HomeGenerative AI EngineerAgentic AI / Generative AI Engineer
Aventine software

Agentic AI / Generative AI Engineer

Aventine software·Tysons, Virginia, US

Posted 2w ago

Full-Time
Apply Now

About the Role

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. 🔑 Key Responsibilities • Design and develop agent-based AI systems using LLMs • Build and maintain LLM-driven workflows using frameworks like LangChain, LangGraph, CrewAI, or AutoGen • Implement RAG (Retrieval Augmented Generation) pipelines using vector databases • 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 ✅ Required Skills & Qualifications • 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 (LangChain, LangGraph, CrewAI, AutoGen, etc.) • Experience with RAG architectures and vector databases (Pinecone, FAISS, Chroma, OpenSearch, 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

What you'll do

  • 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 LangChain, LangGraph, CrewAI, or AutoGen
  • Implement RAG (Retrieval Augmented Generation) pipelines using vector databases
  • 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

Requirements

  • 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
  • ✅ Required Skills & Qualifications
  • 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 (LangChain, LangGraph, CrewAI, AutoGen, etc.)
  • Experience with RAG architectures and vector databases (Pinecone, FAISS, Chroma, OpenSearch, etc.)
  • Solid understanding of AWS services, including:
  • AWS Bedrock
  • S3
  • API Gateway
  • IAM
  • Experience developing RESTful APIs and backend systems
  • Understanding of cloud security, scalability, and monitoring
Back to all jobs