Agentic AI Engineer

Overview

We are seeking an Agentic AI / Generative AI Engineer to design, build, and deploy LLM-powered intelligent agents on AWS. The ideal candidate will have strong Python backend experience
, hands-on exposure to LLMs and agent frameworks
, and experience building production-ready AI applications using AWS cloud services.

This role focuses on developing autonomous and semi-autonomous AI agents
, integrating Large Language Models with enterprise systems, and deploying scalable, secure AI solutions on AWS.

• Design and develop agent-based AI systems using LLMs
• Build and maintain LLM-driven workflows using frameworks like Lang Chain, Lang Graph, CrewAI, or Auto Gen
• Develop backend services and APIs using Python (FastAPI / Flask)
• Integrate LLMs with internal tools, APIs, and data sources
• Deploy, monitor, and scale AI solutions on AWS
• Optimize prompt design, embeddings, and agent decision logic
• Ensure security, reliability, and performance of AI applications
• Collaborate with product, ML, and cloud teams to deliver end-to-end solutions

• Strong proficiency in Python
• Hands-on experience with Large Language Models (LLMs) such as GPT, Claude, LLaMA, or similar
• Experience building Generative AI or Agentic AI applications
• Knowledge of agent frameworks (Lang Chain, Lang Graph, CrewAI, Auto Gen, etc.)
• Experience with RAG architectures and vector databases (Pinecone, FAISS, Chroma, Open Search, etc.)
• Solid understanding of AWS services
  , including:
• AWS Bedrock / Lambda
• S3
• API Gateway
• IAM
• Experience developing RESTful APIs and backend systems
• Understanding of cloud security, scalability, and monitoring