Software & AI Engineer

Available · AI Engineering roles · Open to remote

I build production software end-to-end across product, infrastructure, and applied AI. Eight years engineering systems that move from architecture to shipped product.

View Work →
Role · Full Stack + AI
Stack · Python · React · AWS
Focus · LLMs · RAG · Agents
Education · MS @ RIT · 3.94 GPA
— 01

ABOUT me

I BUILDAI SYSTEMSthat ship

Software engineer with 8 years shipping production systems across healthcare AI, biotech, and enterprise. My work spans backend APIs, React frontends, LLM-integrated pipelines, and the cloud infrastructure underneath — taking complex systems end-to-end.

Most recently at PictorLabs.ai— a UCLA spinoff in digital pathology — fine-tuning Google's PathFoundation vision model, building LLM tooling with Claude API and LangGraph, and leading delivery of an AI virtual staining pipeline for whole slide images.

I'm at my best where AI engineering meets real production engineering — training pipelines, retrieval systems, API design, and the infrastructure that holds it all up. Engineering fundamentals first, frameworks second.

BUILD

Production systems end-to-end

LEARN

AI fundamentals from first principles

SHIP

Product, infra, and model pipelines

Education
MS Software Engineering — Rochester Institute of TechnologyNew York, USAGPA 3.94
B.Tech Mechanical Engineering — ITM UniversityGurgaon, India
Certifications
Anthropic
Model Context Protocol: Advanced Topics
Introduction to Model Context Protocol
Claude Code in Action
Claude with Amazon Bedrock
Introduction to Agent Skills
Introduction to Subagents
DeepLearning.AI
Retrieval Augmented Generation
Agentic AI
PyTorch & Deep Learning
— 02

WORK history

01
AI & FULL STACK ENGINEER
PictorLabs.ai — AI Digital Pathology (UCLA Spinoff)Remote · India
Claude APILangGraphPyTorchKafkaReactDjangoAWS ECS/EKS
Jun 2025 — Feb 2026
LLM-powered internal tooling using Claude API and LangGraph — RAG over clinical documentation, multi-step agent workflows for automated reasoning by clinical and engineering teams.
Fine-tuned Google's PathFoundation on histopathology images in PyTorch; built full training pipeline with OpenSlide patch extraction and Macenko stain normalization.
Led delivery of ClearStain — AI virtual HE staining pipeline for unstained brightfield WSIs; owned Django API, Kafka orchestration, TorchServe model serving.
Built adaptive chunked multipart upload (React Web Workers + S3) with concurrent worker pool, exponential backoff, and resumable support for multi-tenant SaaS.
Built candidate data management portal using Python/Django REST Framework and React.js, processing structured workforce data across organizations.
Led React 15→18 migration, optimizing performance via Concurrent Rendering and React Suspense; ensured full backward compatibility.
Lead dev of the Entitlement Engine — insurance claim eligibility API serving 40,000+ users weekly at 99% uptime via optimized Node.js architecture.
Monolith→micro-frontend migration enabling independently deployable release cycles and faster iteration across teams.
Serverless event-driven Python data pipelines using AWS Lambda, API Gateway, S3, SQS, and CloudWatch.
Cross-functional frontend architecture and reusable React components deployed across multiple Kroger entities in an enterprise agile environment.
Built test suites with Jest and React Testing Library, increasing coverage by 50%.
Built event registration and CEU platforms with automated CI/CD pipelines using React, Node.js, Express, MongoDB, and RESTful APIs.
Computer vision-based automated image classification using Python and OpenCV — eliminated 50+ hours of manual work per event.
— 03

SELECTED work

02
AI · Computer Vision · Production · 2025
CLEARSTAIN PIPELINE

AI virtual HE staining pipeline for unstained brightfield whole slide images, built at PictorLabs.ai (UCLA spinoff, venture-backed). Owned end-to-end: fine-tuned Google's PathFoundation vision model in PyTorch, built Django API with organ/species/diagnosis-based predictor routing, Kafka job orchestration, and TorchServe model serving.

PyTorchDjangoKafkaTorchServeOpenSlideAWS ECS
Closed-source · proprietary
03
RAG · Full Stack · 2025
RAG RESEARCH COPILOT

RAG system for querying research papers — grounding answers in document content with full source citations. Custom semantic search (MiniLM embeddings + ChromaDB), BM25 keyword search, and hybrid retrieval via RRF fusion. No LangChain. Precursor to Cartographer — built to understand retrieval internals from first principles.

FastAPIReactBM25ChromaDBHybrid Search
04
Deep Learning · PyTorch · 2025
TRANSFORMER FROM SCRATCH

Full encoder-decoder transformer implemented in PyTorch — multi-head attention, positional encoding, layer norm, greedy decoding, label smoothing, LR warmup. Trained EN→ES on the Opus Books dataset, end-to-end from "Attention Is All You Need".

PyTorchAttentionTransformersNLP
05
Reinforcement Learning · 2025
RL EXPERIMENTS

Q-learning, DQN (Breakout), and PPO (LunarLander) trained on Gymnasium with Stable Baselines 3 — plus a custom multi-agent dual-taxi environment built from scratch (observation space, reward shaping, training loop). Domain breadth: not just LLMs.

PyTorchGymnasiumSB3DQN · PPO
— 04

TECH stack

01 — AI / LLMs
INTELLIGENCE LAYER
RAGHyDEHybrid SearchRerankingLangChainLangGraphMCPClaude APIQdrantChromaDBPrompt EngineeringLLMOps
02 — ML / Vision
MODELS LAYER
PyTorchscikit-learnOpenCVOpenSlideTorchServetree-sitterFine-tuningHuggingFace
03 — Full Stack
PRODUCT LAYER
React.jsReduxDjangoFastAPINode.jsExpressGraphQLPythonTypeScriptSQL
04 — Infrastructure
INFRA LAYER
AWS S3 / ECS / EKSLambda + SQSApache KafkaDockerCI/CDPostgreSQLMongoDBVercel
05 — Practices
HOW I WORK
Event-driven architectureMicroservicesMicro-frontendsREST API designAgile
06 — Languages
WRITTEN IN
PythonTypeScriptJavaScriptSQLJavaBash
Available for senior AI engineering work
LET'S
build
TOGETHER

If you're building production AI systems and want someone who can go from model training to shipped product — reach out.