AI Engineer

About this role

Job Description
AI Engineer — Senior (7+ Years)


Locations
: Pune, Mumbai, Hyderabad, Bangalore, Mohali, Gurgaon, Noida, Navi Mumbai (On-site)


Shift: Night Shift — 5:00 PM to 2:00 AM IST


Annual CTC

₹ 23.0 - 25.0 LPA


Role Summary
We're hiring a senior AI Engineer to design, build, and deploy production-grade AI/LLM applications on AWS — owning the full lifecycle from architecture through deployment, monitoring, and iteration. You'll work cross-functionally with product, DevOps, and platform teams, and mentor junior engineers.


What You'll Own
End-to-end AI/LLM application architecture on AWS

RAG pipeline design, optimization & evaluation

AI agent frameworks & multi-agent orchestration

Backend APIs/microservices using FastAPI

Observability, tracing & monitoring for AI workloads

Security, guardrails & responsible AI controls

Must-Have Skills


LLMs/Foundation Models
: Production experience with GPT, Claude, Llama, Gemini, or Amazon Nova; prompt engineering, structured outputs, function/tool calling, streaming (SSE/WebSockets)


RAG & Vector Search
: End-to-end RAG pipelines (chunking, embeddings, retrieval, reranking); experience with Pinecone, ChromaDB, Qdrant, or Weaviate; hybrid search (BM25 + dense), Amazon OpenSearch


AI Agents
: Hands-on with LangChain, LangGraph, AutoGen, CrewAI, or Semantic Kernel; multi-agent orchestration; MCP (Model Context Protocol) integration


Backend & Cloud:
Expert Python + FastAPI (async, Pydantic, WebSockets); strong SQL/DB design; AWS (Bedrock, S3, Lambda, ECS/EKS, OpenSearch, IAM); Git/CI-CD


Observability & Evaluation
: LLM-specific tracing/monitoring (Langfuse, Arize Phoenix, Helicone, or LangSmith); evaluation frameworks (Ragas, DeepEval); guardrails, PII detection, hallucination mitigation