Description

Design and build scalable AI systems leveraging large language models, agentic workflows, and retrieval-augmented generation.

This role is on-site.

Responsibilities

• Architect and implement AI agents and agentic workflows using LangGraph and AutoGen.
• Develop retrieval-augmented generation (RAG) pipelines integrating vector databases and embeddings.
• Engineer and optimize prompts for large language model performance.
• Build and integrate REST APIs and backend services to support AI capabilities.
• Design system architecture and manage DevOps practices for cloud-based deployments.

Required Skills

• 14+ years of professional software engineering experience.
• Expert-level proficiency in Python.
• Deep experience with Large Language Models (LLMs) and prompt engineering.
• Hands-on development with LangChain, LangGraph, and AutoGen.
• Strong understanding of vector databases, embeddings, and RAG architectures.
• Proven track record in system design and cloud platform integration.
• Experience building REST APIs and backend service integration.

Preferred Skills

• Experience with AI agent orchestration and complex agentic workflows.
• Strong DevOps background in cloud environments.

Key Skills

Education

Not specified