about

I love chasing hard problems (the kind I'll bang my head against and lose sleep over), then shipping my way out of them. Most recently at Shoppin, where I built an engine that turns a garment photo into a factory-ready sewing pattern in minutes, work that used to take a master pattern-maker days, plus the AI systems around it: the feed, the try-on, the payments. Founding engineer at every startup before this one. I ship fast, I'm at my best debugging the thing nobody else can find, and I'm happiest watching a p95 graph fall.

experience

Senior Product Engineer, Shoppin

Oct 2025 – now · Gurugram, India

Built an agent-based pattern-making engine: garment image/spec → production-ready ASTM sewing pattern in minutes, ~95% accuracy
Shipped an AI-native custom-clothing platform end-to-end: talk it out, design in-browser, get real made-to-order clothes
Owned the recommendation & discovery engine (250K+ items) and the entire e-commerce & payments stack

Founding AI Engineer, Verbaflo.AI

Dec 2024 – Sep 2025 · Gurugram, India

Built the entire backend from scratch for a multi-modal agentic AI platform (Chat / Email / WhatsApp / Voice)
Hybrid RAG pipeline with Milvus: sub-200ms retrieval, 95%+ context accuracy over multi-turn conversations
Shipped multi-provider LLM infra (OpenAI, Anthropic, LLaMA, Qwen) via gRPC, adopted as the standard across every team

Founding AI Engineer, Sidecar

Jul 2025 – Oct 2025 · Remote · Contract

Built a 24/7 autonomous freight-forwarding agent end-to-end for a logistics startup
Reads inbound emails, understands intent with an LLM, and extracts structure from messy shipping docs
Agentic quoting loop that fans out to partner agents and returns the best option with no human in the loop

Founding Engineer, PrudentBit

Jun 2023 – Aug 2024 · Hybrid

Secure file-sharing platform on Azure: 6+ microservices, SAML SSO, OAuth, 2FA, DLP, malware scanning
Enterprise clients: Toyota and UCO Bank
Backend rewrite: 130+ REST APIs; 1s → 30ms latency, 2s → 0.4s page loads

B.Tech in Computer Science, AI/ML specialization · Sushant University · Sep 2021 – May 2025 · 8.9 SGPA

stack

What I reach for.

languages: Python · TypeScript · JavaScript · Go · SQL · C / C++
ai / ml: RAG · agent memory · agent harnesses · evals · guardrails / OWASP-LLM · LLM tracing · model & tool routing · context engineering · multi-agent orchestration · MCP · LangChain · LangGraph · LlamaIndex · PyTorch · Hugging Face · LLM APIs (OpenAI · Anthropic · Gemini)
frontend: React · Next.js · React Native · Tailwind · HTML / CSS
backend: FastAPI · Node.js · Express · Django · gRPC · Celery · RabbitMQ · Prisma · SQLAlchemy · WebSockets / SSE
data: PostgreSQL · Redis · Kafka · Debezium · Apache Pinot · Elasticsearch · MongoDB · Milvus / Zilliz · pgvector
infra / devops: Kubernetes · Docker · AWS · Azure · GCP · Cloudflare Workers · Ray · GitHub Actions · OpenTelemetry · Prometheus · Grafana · Sentry · Playwright · Linux

philosophy

The best software feels like nothing at all. It gets out of the way, it respects your time, and it only shows up when you need it to.

lab

Experiments: some go somewhere, most don't.

001 self-healing agents · my own product: self-healing agents + evals for multi-channel conversational AI [wip]
002 axon v2 · a bigger, faster rewrite of the code-graph engine [wip]
003 ai-ugc-studio · brand brief → finished, post-produced AI UGC video, end to end [shipping]
004 tessera-evals · benchmarking agent memory against the top providers [shipping]
005 gpu-inference · going deep on how GPU inference actually works [research]