Senior AI Software Engineer

GDIT is hiring a Senior AI Software Engineer to build AI applications and agents for the operations team and end users of the cloud platform that supports the National Institute of Allergy and Infectious Diseases (NIAID). You will be the AI developer expert on a team of platform, DevOps, and security engineers, collaborating with other developers and government stakeholders to deliver secure, reliable AI capabilities in a federal cloud environment.

You will design, develop, and integrate software solutions that use large language models (LLMs), retrieval-augmented generation (RAG), vector databases, document processing, and AI agents. This includes an integrated AI assistant for end users and agents that automate platform operations and carry out approved tasks. You will build new AI capabilities and improve existing services for performance, reliability, security, and user experience.

The ideal candidate is a hands-on software engineer who can work across the AI application stack, from backend development and model integration to data processing, automated testing, and deployment. This role requires a strong foundation in software engineering, Python development, API integration, containerization, and AI application architecture.

This role is fully remote!

This role requires you to obtain and maintain a Public Trust and to provide onsite fingerprinting at a designated facility. This investigation may review personal and criminal behavior, financial conduct, foreign influence, as well as other adjudications.

Responsibilities

• Build and deploy LLM-based applications and agents, including APIs, backend services, tool calling, structured outputs, and multi-step workflows.
• Build RAG and document processing pipelines covering ingestion, embeddings, vector search, and reranking.
• Build evaluation into every release with test datasets, regression tests, quality metrics, and human review.
• Work with platform and DevOps engineers to run solutions in production using CI/CD, containers, monitoring, and cost controls.
• Work with security engineers on access control, audit logging, PII handling, approval steps for AI actions, and federal authorization (ATO) documentation.
• Produce technical documentation, architecture diagrams, deployment procedures, and operational runbooks.
• Advise stakeholders, communicate technical tradeoffs and recommended approaches to technical and non-technical audiences, and mentor other engineers.

Required Qualifications

• Bachelor's degree or equivalent experience.
• One of the following:
  • 7+ years of professional software engineering, including 1+ year building LLM-based applications.
  • 5+ years of AI or ML application development, including 2+ years with LLMs.
• At least one LLM application built and supported in production that goes beyond a simple chat interface, such as tool calling, RAG, agents, or multi-step workflows.
• Experience with agent frameworks, such as LangGraph, LangChain, Strands Agents, or CrewAI.
• Strong Python skills, with experience building APIs and backend services, and with Git, automated testing, and code review.
• Experience with major model providers, such as OpenAI, Anthropic, Google, Azure AI, or Amazon Bedrock.
• Experience deploying and debugging applications in the cloud with containers and CI/CD.
• Ability to obtain and maintain a Public Trust.

Preferred Qualifications

• LLM evaluation, tracing, and prompt versioning tools (such as LangSmith, Langfuse, or Ragas).
• Model Context Protocol (MCP) server development and integration.
• AWS, including Amazon Bedrock or Bedrock AgentCore, or relevant AWS certifications (such as Solutions Architect Professional or Generative AI Developer Professional).
• Fine-tuning or customizing foundation models; knowledge bases and vector stores.
• Infrastructure as code (Terraform).
• Containerized microservice architectures.
• Supporting scientific research, federal government, healthcare, or similarly regulated environments.

#GDITFedHealthJobs