AI engineer who ships. I build agentic systems, RAG pipelines and the evaluation harnesses that prove they actually work — not notebooks that die in a folder.
| 🚀 Shipped | 3 production LLM apps · 200+ users · 35% lower latency |
| 🏆 Competed | 🥈 2nd — ByteSize Sage AI National Hackathon · Finalist — Paytm × Sarvam × Logitech |
| ☁️ Certified | AWS Certified Cloud Practitioner (Oct 2025) |
| 🎓 Studied | B.Tech ECE, RCOEM · 8.90/10 · Minor in AI/ML 9.67/10 |
AI Engineer Intern — AI LifeBOT · Jan – Jun 2026
- Built 3 production LLM applications and autonomous agents using LangChain + GPT-4, serving 200+ users.
- Architected end-to-end GenAI pipelines with RAG, vector databases, and real-time streaming, achieving 35% lower latency and 99.5% uptime.
- Developed multi-agent orchestration with approval gates, telemetry, and audit logging.
ML Research Intern — CFM, RCOEM · May – Jul 2025
- Built a clinical prediction system using 1,000+ patient records with biometric feature engineering, achieving 87% accuracy.
- Reduced development time by 30% through pipeline optimization and rigorous cross-validation.
🛰️ ML Guardian — autonomous ML reliability agent
Catches silent production failures — stale upstreams, creeping null rates, renamed columns — before a KPI moves. Runs a scan → score → incident → write-back → remediate loop over DataHub via MCP, naming the exact downstream models at risk and generating fail-fast remediation code. Ships with bundled fixtures: runs with no Docker and no API keys, one env var away from live.
Python FastAPI MCP DataHub Gemini GitHub Actions
🤖 Executive Email Copilot — agent benchmarking environment · Live Demo
A deterministic simulation environment for benchmarking autonomous email agents across classification, prioritization and full action execution, with bounded, numerically stable grading metrics. Four policy modes (heuristic, stress-test, LLM-driven, multi-agent hybrid), episode replay, approval workflows — and published benchmark results with honest findings.
Multi-Agent RAG FastAPI React SciPy PostgreSQL
🎵 music-recsys — production-scale recommender
Two-stage pipeline — two-tower embeddings → ANN retrieval → LightGBM ranker — with a full MLOps loop: event bus, feature updater, online store, model registry, retrain jobs. Interface-first design puts every dependency behind a Protocol, so it runs CPU-only and Windows-native with zero external services, then scales to Kafka/K8s by flipping one config value.
PyTorch LightGBM MLflow Kafka Redis Prometheus
20+ more — agentic platforms, India-market AI, Web3 and IoT — on my portfolio and repos.
| Languages | Python · TypeScript · C++ · SQL · Solidity |
| GenAI & Agents | LangChain · LangGraph · MCP · OpenAI · Azure OpenAI · Gemini · Ollama |
| ML & Data | PyTorch · scikit-learn · XGBoost · LightGBM · ONNX · MLflow · pandas |
| Stores | PostgreSQL · Qdrant · Pinecone · Redis · Supabase · Neo4j |
| Backend & Web | FastAPI · Node.js · Next.js · React · Tailwind |
| Infra | AWS · Azure · Docker · Kubernetes · Kafka · Prometheus · GitHub Actions |