Description

You will build and productionize cloud-native backend services and AI/LLM inference pipelines for real-time and batch workloads.

This role is on-site.

Responsibilities

• Design Python-based APIs and microservices using FastAPI and async patterns.
• Develop agentic AI workflows using LangChain and LangGraph.
• Implement LLM capabilities including RAG, embeddings, vector search, and prompt engineering.
• Deploy and monitor models on Kubernetes using Helm, ensuring observability and SLOs.
• Apply system design principles for caching, concurrency, rate limiting, and reliability.

Required Skills

• Python with 4–6 years of professional experience.
• Strong proficiency in FastAPI and asynchronous programming.
• Experience with Kubernetes, Docker, and Helm for container orchestration.
• Knowledge of cloud infrastructure, preferably Azure AKS.
• Understanding of microservices architecture and distributed systems.
• Experience with LLM integration, including vector databases and embeddings.
• Familiarity with CI/CD automation and testing standards.

Preferred Skills

• Hands-on experience with LangChain and LangGraph for agentic workflows.
• Background in model monitoring, governance, and performance tuning.

Key Skills

Education

Any Graduate