Description

Experience: 4–6 Years

Key Responsibilities:
Build and productionize cloud-native backend services and AI/LLM inference pipelines
Design Python-based APIs and microservices using FastAPI and async patterns
Develop agentic AI workflows using LangChain / LangGraph
Implement LLM capabilities: RAG, embeddings, vector search, prompt engineering, model versioning
Deploy and monitor models for real-time & batch inference
Work on Kubernetes-based deployments with Helm
Build event-driven, scalable, and resilient architectures
Ensure observability, CI/CD automation, SLOs, and testing standards
Apply strong system design principles (caching, concurrency, rate limiting, reliability)

Skills Required:
Python, FastAPI
LLM / GenAI / AI Engineering
RAG, Vector DBs, Embeddings
Kubernetes, Docker, Helm
Cloud (Azure / AKS preferred)
Microservices & System Design

Good to have:
LangChain / LangGraph
Model monitoring & governance
Performance tuning & distributed systems
Frontend collaboration exposure

Key Skills

Education

Any Graduate