Description

You build and deploy production-grade agentic AI systems, focusing on multi-agent orchestration, RAG pipelines, and scalable backend infrastructure.

This role is on-site.

Responsibilities

• Design and implement agentic workflows using LangGraph, Semantic Kernel, AutoGen, or similar frameworks.
• Build and optimize RAG pipelines, including data ingestion, chunking strategies, embeddings, vector databases, and hybrid search.
• Develop production-grade LLM applications with tool/function-calling, structured outputs, and evaluation mechanisms.
• Engineer scalable microservices and APIs (REST/RPC) using CI/CD, Docker, and Kubernetes on AWS, Azure, or GCP.

Required Skills

• 5+ years of software engineering experience with expert-level proficiency in Python.
• Hands-on experience with LLMs (GPT, Claude, Gemini) beyond simple API calls.
• Strong understanding of multi-agent systems, planning, and autonomous execution.
• Practical knowledge of vector databases (Pinecone, Chroma, FAISS) and embedding models.
• Experience with containerization (Docker, Kubernetes) and cloud platforms (AWS, Azure, GCP).
• Familiarity with CI/CD pipeline construction and microservices architecture.
• Proficiency in at least one additional language: Java, Go, or TypeScript.

Preferred Skills

• Experience with Semantic Kernel or AutoGen specifically.
• Background in MLOps and production ML model deployment.

Key Skills

Education

Any Gradute