- Senior AI/ML + Product Engineer
- AI/ML engineering: 4 years
- AI product engineering: 5 years
- Focused on production delivery: reliability, observability, and measurable impact
- Specializing in AI agents, LLM/NLP products, RAG search, and ML/DL pipelines
Senior AI/ML + Product Engineer focused on shipping production-grade AI systems end-to-end.
I bring 4 years of AI/ML engineering experience and 5 years of AI product engineering experience, turning models into reliable, scalable features with measurable business impact.
AI in industry is moving from "chatbots" to full systems: agentic workflows, retrieval + reasoning, measurable evaluations, secure enterprise deployments, and cost/latency-aware serving. That is where I build.
- AI agents and tool-using workflows: routing, state machines, fallbacks, permissions, safety controls
- LLM/NLP products: RAG assistants, summarization, extraction, classification, relevance/reranking
- ML/DL systems: training -> evaluation -> deployment -> monitoring (drift and data quality)
- Data and big data pipelines: batch/stream processing, analytics-ready datasets, experimentation loops
- Fullstack AI products: APIs, dashboards, multi-tenant platforms, usage metering, SLAs
- Languages: Python, SQL, TypeScript, Bash (plus Rust/Go/C++/Java as needed)
- Frontend: React, Next.js, Tailwind, MUI, Chakra UI, shadcn/ui
- Backend: FastAPI/Django, NestJS/Express, REST/gRPC, WebSockets, auth (JWT/OAuth)
- Data: PostgreSQL (pgvector), Redis, MongoDB/DynamoDB, Elasticsearch/OpenSearch, vector DBs (Pinecone/Weaviate/Milvus/FAISS), BigQuery/Snowflake/Redshift
- MLOps/Infra: Docker, Kubernetes/ECS, Terraform, GitHub Actions, Airflow/Dagster/Prefect, Kafka/PubSub/Kinesis, OpenTelemetry/Prometheus/Grafana, ELK, Sentry, MLflow/W&B
I care about correctness, reliability, maintainability, and observability, with pragmatic tradeoffs between accuracy, latency, and cost.
If you are building agentic AI or production ML systems, I am happy to collaborate.