Full-Stack AI Engineer (2–4 years)
Location : Remote / Bangalore
Employment Type : Full-time
Department : Engineering
Industry Type :
IT Services & Consulting
Role Category :
Software Development – Full-Stack (AI)
Role & Responsibilities
Integrate
OpenAI
and other provider APIs (Gemini, etc.) into
Next.js + Node.js
features; handle streaming, function / tool calling, retries, and rate limits.
Build pragmatic
RAG
plumbing (chunking, embeddings, retrieval) and expose secure backend endpoints; wire a vector store (e.g.,
Pinecone ).
Add lightweight evaluation (groundedness / relevance) and release checks; log token / cost / latency with basic dashboards.
Own CI / CD for these services (GitHub Actions), secrets, and environment configs.
Desired Candidate Profile
2–4 yrs shipping
TypeScript / React (Next.js) + Node.js
features with real API integrations.
Hands-on with
OpenAI Node SDK
(Responses API) and at least one other provider (Gemini).
Practical RAG experience and familiarity with a vector DB (Pinecone) and orchestration (LangChain.js or equivalent).
Education B.E / B.Tech / MCA (or equivalent).
Key Skills
TypeScript, React, Next.js, Node.js,
OpenAI (Responses API) ,
Google Gemini , RAG, Embeddings,
Pinecone , LangChain.js, REST / GraphQL, Docker, GitHub Actions, Observability
Notice Period :
Immediate–30 days preferred
Ai Engineer • India