AI product engineering
Retrieval, OCR, model integrations, APIs, and interfaces connected into complete user workflows.
AI ENGINEER / ML SOFTWARE ENGINEER
AI that works
in the real world.
Aravinda Raman Jatavallabha
I build production AI systems—from clinical document pipelines and retrieval to full-stack applications—and research how to make language models more dependable.
WHAT I BRING TO A TEAM
ML systems & data
Forecasting, orchestration, model monitoring, and cloud delivery across healthcare and public safety.
Research into practice
LLM evaluation, privacy, and evolving representations—with papers and code you can inspect.
01 / SELECTED ENGINEERING
The problem, the build,
the result.
The problem, my contribution, the system, and the result. A closer look at how I take AI beyond an isolated model.
LONG HEALTH · JUN 2025–PRESENT
EvalPath
From fragmented medical records to structured clinical documentation.
The problem
Specialized medical evaluations bring together scanned records, physician–patient conversations, exam findings, and final reports. Each stage needs to connect to the next.
What I own
End-to-end platform engineering: document ingestion and indexing, asynchronous OCR, retrieval, transcription, structured report generation, and role-aware physician portals.
How I built it
- Document infrastructure. AWS Lambda, ECS, S3, RabbitMQ, and Textract for ingestion and processing.
- Clinical AI workflows. ChromaDB retrieval, OpenAI and Anthropic integrations, ICD-10 inference, and Whisper transcription.
- Product delivery. Angular/NestJS interfaces, case assignment, four-role access control, exports, monitoring, and pipeline alerts.
Records & audio→OCR & transcription→Retrieval & extraction→Structured reports
35%higher document throughput*
50%less documentation & triage time*
*Outcomes reported in my career materials. Public baselines and measurement periods are unavailable. Employer systems and clinical data are private.
INDEPENDENT PROJECT · CREATOR
CausEval.
Do your AI tests catch missing instructions?
The problem
A passing evaluation suite can still miss important prompt instructions. Test pass rate alone does not show which behaviors the suite actually checks.
My contribution
I created CausEval to extract behavioral rules, map them to evaluations, remove one instruction at a time, and compare repeated runs. The result is an inspectable account of detected and missed changes.
BUNDLED EXAMPLE / FIXTURE RESULTS
Eval pass rate100%
Trace coverage75%
Causal rule coverage42%
12 rules · 9 evaluations · 5 rule removals detected
Reproducible example data, not a live-model benchmark or adoption claim.TRY IT LOCALLY
npx causeval demoNo API key needed for the bundled example.
SMARTPROTECT · MAY 2024–JUN 2025
Forecasting for
public safety.
Built forecasting and data workflows to support dispatch planning and staffing decisions.
- Compared ARIMA, Prophet, and LSTM models for call-volume prediction.
- Built Airflow/Snowflake pipelines across 1.2M+ dispatch records.
- Connected forecasts to staffing recommendations, drift detection, retraining, and role-aware dashboards.
20% reported forecast-accuracy improvement18% reported overtime reduction
Career-material figures; public baselines and evaluation periods are unavailable.
Read my managers’ recommendations ↗DRDO / CAIR · JAN–JUN 2023
Language models
for evolving data.
Researched how models can update their representations as language and interaction patterns change.
- Designed and experimented with incremental BERT representations and temporal graph learning.
- Built streaming NLP workflows to update token representations without full retraining.
- Contributed model design and experiments to the coauthored ICPR research.
ICPR 2024 conference · Springer chapterPublished research / contributing author
Read the publication ↗02 / EXPERIENCE
The work behind
the skill set.
Clinical AI, public safety, industry analytics, and academic research. Hands-on responsibility from experimentation through software delivery.
Jun 2025–Present
Long Health
AI Engineer
AI platforms & full-stack systems
Built and maintained EvalPath across cloud infrastructure, document AI, retrieval, model integrations, and physician-facing workflows. Partnered with clinical and compliance teams on privacy-sensitive data handling.
Python · TypeScript · Angular · NestJS · AWS · RabbitMQ
May 2024–Jun 2025
SmartProtect Public Safety Solutions
Data Science Intern / Co-op
Predictive analytics & ML systems
Developed 911 call-volume forecasts, ETL pipelines, staffing recommendations, and internal dashboards. Implemented drift detection, versioned data, and automated retraining; explored dispatcher transcript analysis using LLMs.
Airflow · Snowflake · SageMaker · Flask · Spring Boot · Angular
Aug 2024–May 2025
North Carolina State University
Graduate Teaching Assistant
Machine learning & efficient inference
Supported CSC 522: Automated Learning and Data Analysis with Prof. Thomas Price, and CSC 591/791: Real-Time AI and Machine Learning Systems with Prof. Xipeng Shen. Evaluated projects, developed grading rubrics, held office hours, and helped students with validation, model selection, quantization, and inference trade-offs.
scikit-learn · TensorRT · ONNX Runtime · ML evaluation
Jan–Jun 2023
DRDO · Centre for AI & Robotics
Machine Learning Researcher
Streaming NLP & temporal graph learning
Implemented temporal graph models in PyTorch Geometric and incremental BERT workflows for evolving text. Conducted model-design and experimental work on dynamic representations and semantic change.
PyTorch · PyG · BERT · Temporal GNNs
May–Jul 2022
Merkle
Data Science Intern
Retail ML & data engineering
Led a four-person internship team working with 10M+ retail records. Built XGBoost, LightGBM, and LSTM models; engineered ETL across 16M+ rows using PySpark, SQL, and Snowflake; delivered pricing and segmentation dashboards. The project received the Stellar Team Award.
PySpark · SQL · Snowflake · XGBoost · Power BI · Tableau
Mar 2021–Jun 2022
Manipal Institute of Technology
Machine Learning Researcher
Medical imaging & network prediction
Compared VGG-16, MobileNet, InceptionV3, and XceptionNet for pediatric bone-age assessment. Worked on LSTM/Bi-LSTM link-quality prediction and automated data, training, and API workflows.
TensorFlow · Keras · Airflow · SageMaker · Flask
EDUCATION
A foundation in computer science.
Master of Computer Science
North Carolina State University / 2023 - 2025
Data Science specialization / GPA 4.0 of 4.0
View credential ↗
Bachelor of Technology
Manipal Institute of Technology / 2019 - 2023
Information Technology / GPA 8.64 of 10
View credential ↗B.Tech. minor: Big Data Analytics. Graduate coursework includes NLP, Generative AI, Machine Learning with Graphs, Privacy in AI, and Database Management Systems.
Professional certificates
- Data Science Specialization / NC State UniversityCertificate ↗
- Machine Learning Specialization / Stanford, CourseraCertificate ↗
- Deep Learning Specialization / DeepLearning.AI, CourseraCertificate ↗
- AI Summer School / IIIT HyderabadCertificate ↗
03 / PUBLICATIONS & RESEARCH
Research with
a practical question.
Language models, dynamic representations, and applied machine learning. Published work and work in progress, with their respective records.
Google Scholar6Published
1Accepted
3Preprints
4Manuscripts
Every work is labeled by status.
Publisher and author-hosted records are linked below.
14 research works
TrustBench: Benchmarking Trustworthy Large Language Models with Cost and Stability Metrics
Deployment-oriented evaluation of LLM behavior, repeatability, confidence, and cost.
Compares five proprietary models across ambiguity, safety, and multi-step tasks with repeated trials. Distinguishes stable behavior from verified task correctness and examines how pricing changes value comparisons.
Prompting for LLM Security and RAG: A Survey from Zero-Shot to Automatic Prompt Optimization (APO) and Prompt-Injection Defenses
Prompting methods and security considerations for retrieval-augmented and other security-sensitive LLM workflows.
A practitioner-oriented survey connecting prompting methods, automatic optimization, prompt injection, and RAG poisoning. Organizes methods around accuracy, cost, and security trade-offs.
Learning Dynamic Representations in Large Language Models for Evolving Data Streams
Incremental language modeling and dynamic contextualized word embeddings for streaming text.
Coauthored research on incremental BERT and dynamic graphs for changes in language over time. My primary contribution was model design and experiments. Springer lists the author as J. Aravinda Raman.
SDN-Based Multipath Data Offloading Scheme Using Link Quality Prediction for LTE and WiFi Networks
Sequence models for link-quality prediction and data offloading in heterogeneous networks.
Studies LSTM and bidirectional LSTM predictions using signal strength and packet data rate to inform LTE/WiFi offloading. My primary contribution was model design and experiments.
Diabetes Prognosis using Machine Learning: A Comparative Analysis of Classification Algorithms
Comparison of K-nearest neighbors, random forests, and neural networks for diabetes prediction.
A comparative modeling study examining preprocessing, feature engineering, and classifier performance. Reported research performance should not be interpreted as clinical validation.
Privacy Awareness in Large Language Models: Input Regurgitation and Prompt-Induced Sanitization for HIPAA and GDPR Compliance
Input regurgitation and prompt-based sanitization in privacy-sensitive LLM applications.
Studies sensitive-information leakage and prompting strategies on synthetic inputs. These experiments examine privacy behavior; they do not establish regulatory compliance for a deployed system.
Dynamic Graph Representation Learning using Temporal and Topological Information
Temporal graph learning that combines time-aware message passing, topology, and node information.
The TDGNN framework investigates prediction in dynamic interaction networks using temporal information and graph structure.
Publication link pending
Tesla's Autopilot: Ethics and Tragedy
Ethical analysis of autonomous-driving incidents, responsibility, and system limitations.
A case study applying a seven-step ethical decision-making process to user behavior, technology limitations, and policy considerations.
Deciphering Air Travel Disruptions: A Machine Learning Approach
Regression and sequence-model comparisons for flight-delay prediction.
Examines delay components and flight characteristics using regression models and LSTM variants. Explores which factors can inform flight planning.
Pediatric Bone Age Assessment using Deep Learning Models
Comparative evaluation of pretrained convolutional networks for bone-age assessment.
Compares VGG-16, InceptionV3, XceptionNet, and MobileNet using error measures on pediatric X-ray data.
Using Transformer-Based Models to Optimize Inventory Replenishment Decisions in Dynamic E-Commerce Markets
Attention-based modeling for inventory decisions under changing demand and seasonality.
Investigates multi-head attention for historical sales, promotions, pricing, and external signals. This work is under review; no publication is claimed.
No public link
Improving Fairness in Visual Recognition through Feature Distillation and Adversarial Debiasing
Feature distillation and representation learning for fairness in visual recognition.
Explores an MMD-based distillation objective to reduce disparity while maintaining task performance. A manuscript, with no peer-reviewed publication status claimed.
Multimodal Conversation Derailment Detection: An Integrated Framework for Early Risk Assessment
Combining language and visual features to study conversation derailment.
A hierarchical transformer approach integrating BERT-based text encoding and visual features. Shared as an author-hosted manuscript.
Graph Contrastive Learning for Optimizing Sparse Data in Recommender Systems with LightGCL
A manuscript exploring graph contrastive learning and sparse recommendation data.
Examines SVD-based augmentation and collaborative graph representations. This listing does not claim invention of the existing LightGCL method.
No matching research
Try another title, topic, or publication status.
Publication links are provided where available. Accepted work, preprints, and manuscripts are listed separately from published papers. Research summaries are concise descriptions, not verbatim abstracts.
04 / PROJECTS & CODE
More work,
open for inspection.
LLM APPLICATION
CoveredAI
Built a full-stack health-insurance document assistant: upload plans, retrieve relevant passages, ask questions, compare coverage, and export personalized PDF reports.
React / TypeScript / Flask / LangChain / FAISS
View repository ↗RETRIEVAL
Legal Query AI Assistant
Retrieval-augmented document question answering using language models and vector search.
GPT / LangChain / RAG
View repository ↗COMPUTER VISION
Lane Detection
SegNet and LSTM-based lane detection, lane curvature, and vehicle-offset estimation from video.
SegNet / LSTM / OpenCV
View repository ↗TIME SERIES
Store Demand Forecasting
Item-level sales forecasting with neural networks and comparisons against statistical and tree-based models.
CNN / BiLSTM / XGBoost
View repository ↗ML PIPELINES
Customer Churn Prediction
A machine learning pipeline spanning orchestration, training, model storage, and API-based inference.
Airflow / AWS / Docker / Flask
View repository ↗MEDICAL IMAGING
Brain MRI Segmentation
U-Net segmentation of brain MRI images for pixel-level tumor-region prediction.
U-Net / TensorFlow / Keras
View repository ↗LLM APPLICATION
Cold Email Generator
Matches job descriptions with portfolio skills through retrieval to draft personalized outreach.
LLaMA3 / ChromaDB / Streamlit
View repository ↗GENERATIVE VISION
Image-to-Image Translation
Unpaired image translation across visual domains using a CycleGAN.
CycleGAN / PyTorch
View repository ↗DATABASE SYSTEMS
Wolf Parking
A database management project for parking operations.
Database management
View repository ↗MEDICAL IMAGING
Chest X-ray Classification
A research project exploring COVID-19 classification from chest X-ray images.
Deep learning / Computer vision
View repository ↗RECOMMENDATION
Movie Recommendation
Collaborative filtering for personalized movie recommendations.
Recommender systems
View repository ↗11 projects
05 / TECHNICAL CAPABILITIES
Tools I actually reach for.
The technologies I use to connect model behavior, data infrastructure, and the product experience.
LLMs & retrieval
RAG, LangChain, OpenAI, Anthropic, Hugging Face, LLaMA, ChromaDB, FAISS, prompt engineering, structured extraction, and evaluation.
Applied in EvalPath ↗Modeling & research
PyTorch, TensorFlow, Keras, scikit-learn, PyG; temporal graphs, NLP, time-series forecasting, computer vision, and recommendation.
Explore the research ↗Software engineering
Python, TypeScript, JavaScript, SQL, Angular, React, NestJS, Flask, REST APIs, role-aware interfaces, and Git.
Inspect project code ↗Data & cloud delivery
AWS Lambda, ECS, S3, ECR, SageMaker, Textract; Airflow, RabbitMQ, Docker, Spark, Snowflake, Azure, Power BI, and Tableau.
See the experience ↗06 / SERVICE & RECOGNITION
Contributing to
the wider community.
Peer reviewing, teaching, and participation in the research community.
IEEEACCESS
JANUARY 2026 - PRESENT
Invited reviewer / AI & ML
Invited to review AI and machine learning manuscripts for IEEE Access, evaluating technical quality, originality, methodology, and clarity.
Invited reviewer role · Since January 2026
JMIRPUBLICATIONS
AUGUST 2026 - PRESENT
Peer Reviewer (Invited)
Invited by JMIR Publications to review submitted research manuscripts in the field of AI with a focus on medicine.
Science & Technology · Medical AI
JANUARY 2026 - PRESENT
Sigma Xi full member
Elected to full membership through peer nomination and review.
NC STATEUNIVERSITY
AUGUST 2024 - MAY 2025
Teaching & mentorship
Graduate teaching assistant for Automated Learning and Data Analysis and Real-Time AI and Machine Learning Systems.
Supported project evaluation, grading rubrics, model selection, and efficient inference.
INDUSTRY RECOGNITIONStellar Team AwardMerkle internship cohort
Team recognition for the internship project.
07 / COLLEAGUE PERSPECTIVES
From the people
I've worked with.
“His attention to detail, analytical insight, and dedication made him an invaluable asset to our team.”
Read full recommendation
I've had the pleasure of working with Aravinda Jatavallabha as part of the SmartProtect Public Safety Solutions team, where he served as a Data Science Intern over the past six months. Aravinda's contributions to building out our predictive analytics framework for public safety have been both impactful and highly innovative. His work, especially in structuring and analyzing complex datasets, significantly advanced our ability to deliver tailored, data-driven solutions to our clients.
Aravinda brings deep technical expertise to his work, combined with a genuine commitment to understanding and solving client challenges in public safety. His attention to detail, analytical insight, and dedication made him an invaluable asset to our team, and his contributions will continue to benefit both our company and the customers we serve.
“He was a valued team member with great communication skills and someone I trusted to bring both integrity and innovation to the table.”
Read full recommendation
I had the pleasure of working with Aravinda during his time at SmartProtect, where he made a lasting impact on our AI/ML initiatives. From day one, he brought thoughtfulness and a sharp technical mindset to every challenge. Whether he was building early prototypes or helping us think through how machine learning could meaningfully support public safety operations, Aravinda consistently delivered high-quality work and insightful ideas.
What stood out most was his willingness to dive deep, learn fast, and look for ways to make the work better, not just from a technical standpoint, but in a way that aligned with the mission of serving first responders. He was a valued team member with great communication skills and someone I trusted to bring both integrity and innovation to the table.
Any team would be lucky to have Aravinda on board, and I'm excited to see where his journey takes him next.
Recommendations are reproduced with light punctuation cleanup for readability. Links lead to the recommenders' profiles.
08 / PROFESSIONAL RECORD
A clear record.
A source for every chapter.
For hiring teams, research collaborators, and professional reviewers: a direct path to my work, contributions, and credentials.
Applied AI.
Documented contributions.
My work connects dependable language-model workflows with the infrastructure needed to use them: retrieval, evaluation, document processing, and learning from evolving data.
Publication-name variants include Aravinda Raman Jatavallabha, Aravinda Jatavallabha, Aravinda Raman, and J. Aravinda Raman. Use each publisher’s original author listing when citing a work.
- Engineering ownership
- EvalPath architecture and workflows; SmartProtect forecasting and ML systems.Contribution summaries ↗
- Original software
- CausEval: prompt-rule mutation testing and inspectable evaluation reports.Repository & attribution ↗
- Scholarly work
- Published papers, an accepted work, preprints, and manuscripts with distinct status labels.Complete research bibliography ↗
- Service & recognition
- Invited reviewing, Sigma Xi full membership, graduate teaching, and a Merkle team award.Roles & membership documents ↗
- Professional perspectives
- Recommendations from two SmartProtect co-founders, including relationship and date.Read recommendations ↗
- Academic credentials
- NC State MCS and Manipal B.Tech., with linked credentials.Education & certificates ↗
This portfolio presents my professional record and links to supporting materials. Employer outcomes are reported from my career materials; independent adoption, citation totals, and completed-review counts are not asserted here.
09 / LET’S CONNECT
Building an AI team?
Let’s talk.
I’m interested in AI Engineer, ML Software Engineer, and applied AI roles where I can own meaningful systems from model to product. For hiring conversations, share the role, team, and problem you’re solving.
aravindaraman14@gmail.com ↗