16 Nov
|
Indegene
|
India
Must-have skills
2–7 years in software engineering, with at least 1–2 years building production AI/LLM applications.
Robust Python; working knowledge of TypeScript.
Hands-on RAG: embeddings, vector search, chunking strategies, reranking and retrieval evaluation.
Knowledge graph experience with Neo4j (or similar) and Cypher.
Built at least one multi-agent or agentic workflow with LangGraph, AWS Strands, Langchain, CrewAI, AutoGen or similar.
Backend: Django or FastAPI, REST APIs, async processing, PostgreSQL, Redis.
Front end: React or Next.js.
AWS: deploying and running services (ECS/EKS or Lambda, S3, RDS, IAM); Bedrock is a plus.
Demonstrated LLM cost optimization with measurable results.
Testing discipline: unit and integration tests, Git, CI/CD.
Comfortable using AI coding tools (Claude Code or similar) while owning the quality of what ships. Valuable to have
MCP server development and A2A (agent-to-agent) protocols.
LLM observability and evaluation tools: Langfuse, Arize Phoenix, Ragas, DeepEval, promptfoo.
Fine-tuning or small-model work (LoRA, distillation) for cost-sensitive tasks.
Open source contributions, technical blogs or public AI projects.
📌 Ai Engineer Bengaluru (India)
🏢 Indegene
📍 India