Principal AI Engineer

Location: Onsite McLean VA or Richmond VA
Duration: 7 Months (Contract)

We are seeking a highly skilled Principal AI Engineer to lead the design and implementation of next-generation Agentic AI solutions. This is a hands-on builder role requiring deep expertise in Generative AI full-stack Python development and AWS cloud architecture.

The ideal candidate will be responsible for transforming experimental AI prototypes into scalable production-grade autonomous systems that drive business value.

• Design and deploy multi-agent systems using LLM orchestration frameworks such as LangGraph and CrewAI
• Build intelligent workflows to automate complex business processes and improve operational efficiency

• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines
• Leverage Amazon Bedrock and vector databases such as OpenSearch and Pinecone
• Ensure high performance with defined latency and accuracy benchmarks

• Build scalable backend services using FastAPI and Python 3.10
• Collaborate with frontend teams to integrate AI capabilities into React-based interfaces
• Implement real-time and streaming AI-driven user experiences

• Implement prompt safety mechanisms output validation and content moderation
• Conduct bias evaluation and compliance checks for enterprise-grade AI systems

• Establish automated evaluation frameworks (e.g. Ragas DeepEval)
• Implement observability and monitoring using tools like LangSmith and OpenTelemetry
• Develop and maintain CI/CD pipelines for AI models prompts and backend services

• Experience with LLMs such as Claude GPT-series and LLaMA
• Hands-on with Hugging Face Transformers and PEFT techniques
• Familiarity with orchestration frameworks like LangChain and LangGraph

• Strong experience in autonomous agents tool usage function calling and state management

• Expertise in Python FastAPI Pydantic and asynchronous programming

• Strong experience with AWS services including:
  • Amazon Bedrock
  • SageMaker
  • AWS Lambda (Serverless)
  • RDS / pgvector

• Experience with AI monitoring tracing and evaluation tools

• 10 years of experience in Software Engineering
• 7 years of backend development with Python
• 2 years of hands-on experience with Generative AI / LLMs
• 5 years of experience designing and deploying AWS-based solutions

• Experience building production-grade AI systems at scale
• Strong understanding of distributed systems and microservices architecture
• Familiarity with frontend technologies (React) for AI integration