AI Engineer; Mid–Senior) AI Agents Federal

Federal US Citizens ONLY - NO SUBS, NO Subcontracting, NO outside firms.

Hands-on experience with designing and building AI Agents

UGT is hiring a Mid-to-Senior AI Engineer to design, build, and support production-grade AI Agents and Generative AI solutions for a leading U.S. Department of Energy laboratory.

This is a hands-on engineering role focused on building AI agents, Retrieval-Augmented Generation (RAG) solutions, and the data pipelines and integrations that support them. The environment spans AWS Bedrock, Google Gemini for Government, and Microsoft Copilot
, providing the opportunity to work across multiple enterprise AI platforms.

The ideal candidate combines strong Python/software engineering skills with practical experience building LLM-powered applications
. You do not need to be an expert in every cloud or AI technology listed, but you should have hands-on experience taking Generative AI solutions beyond experimentation and into usable, reliable applications.

The engineer will work closely with cloud, security, data, and business teams and will help mentor a junior AI engineer as the laboratory expands its AI capabilities.

• Design and build AI Agents and agentic workflows using Large Language Models (LLMs).
• Develop AI agents capable of interacting with enterprise data, APIs, applications, and approved tools.
• Build and enhance RAG applications using enterprise documents and structured/unstructured data.
• Develop Python services, APIs, and backend components supporting AI applications.
• Build data pipelines for document ingestion, parsing, chunking, metadata enrichment, embeddings, indexing, and retrieval.
• Implement vector search and retrieval capabilities to provide reliable grounding for LLM applications.
• Develop solutions using AWS Bedrock, Google Gemini/Vertex AI, Microsoft Copilot/Azure AI
  , or comparable cloud AI platforms.
• Support the laboratory's centralized AI control plane for model access, monitoring, governance, usage tracking, and cost management.
• Integrate AI solutions with enterprise applications, databases, document repositories, APIs, and other data sources.
• Implement appropriate authentication, authorization, logging, auditing, and data-access controls.
• Develop testing and evaluation processes for AI agents and RAG solutions, including accuracy, retrieval quality, reliability, latency, and cost.
• Monitor and troubleshoot production AI applications and supporting services.
• Containerize and deploy AI applications using modern Dev Ops and CI/CD practices.
• Collaborate with cybersecurity, cloud engineering, data teams, subject-matter experts, and business stakeholders.
• Document architectures, integrations, workflows, and operational procedures.
• Provide technical guidance and mentorship to a junior AI engineer.

• Bachelor's degree in Computer Science, Engineering, Information Technology, Data Science, Artificial Intelligence, or related field, or equivalent professional experience.
• 4+ years of professional software engineering, application development, data engineering, or related technical experience.
• 2+ years of hands-on Python development experience.
• Practical experience developing applications using Generative AI/LLMs
  .
• Hands-on experience with AI Agents, RAG, or LLM-based application development
  .
• Experience integrating applications with APIs and enterprise data sources.
• Understanding of embeddings, vector search, prompt engineering, context management, and LLM application patterns.
• Experience with at least one major cloud environment such as AWS, Google Cloud, or Microsoft Azure
  .
• Familiarity with Git, CI/CD, containers, and modern software development practices.
• Strong analytical, troubleshooting, and problem-solving skills.
• Ability to work independently while collaborating effectively with technical and non-technical stakeholders.

• Experience with AWS Bedrock
  , including Bedrock models, Knowledge Bases, Agents, or related services.
• Experience with Google Gemini / Vertex AI
  .
• Experience with Microsoft Copilot or Azure AI
  .
• Experience with agent frameworks such as Lang Graph, Lang Chain, Semantic Kernel, Auto Gen, CrewAI
  , or similar.
• Experience with vector databases or search technologies such as Open Search, pgvector, Pinecone, Weaviate, Milvus, FAISS
  , or similar.
• Experience building production RAG pipelines involving document ingestion, chunking, embeddings, retrieval, and evaluation.
• Experience with Docker and/or Kubernetes
  .
• Familiarity with Terraform or Infrastructure as Code.

• Understanding LLM security, governance, observability, evaluation, and cost management
  .
• Experience working in DOE, federal government, national laboratory, or another regulated/security-conscious environment.
• Previous experience mentoring junior engineers.