AI Software Engineer

Role overview Build and operate production AI agents for software and operational workflows in security-sensitive environments. This hands-on engineering role spans agent design, retrieval and tool integrations, cloud deployment, and evaluation, while partnering with product and engineering teams to turn promising AI use cases into reliable capabilities.

Responsibilities - Design agent systems with multi-step orchestration, emphasizing reliability, traceability, and measurable quality. - Develop retrieval components, including data ingestion, embeddings, chunking, search, and re-ranking, and connect agents to knowledge bases, vector stores, APIs, and enterprise tools. - Build Model Context Protocol servers and clients to connect agents with organizational tools and information. - Deploy and maintain research and development infrastructure using Kubernetes on AWS, Terraform, Helm, and GitOps practices. - Create evaluation and regression suites for groundedness, faithfulness, relevance, and retrieval quality, and run them in continuous integration. - Work with product partners to identify valuable workflows and advise on agent design, model choice, and quality expectations.

Requirements - At least two years of full-time software, machine-learning, or AI engineering experience, including production work shipping systems based on large language models. - Practical experience building tool-using agents and multi-step workflows with LangGraph, LangChain, or similar frameworks. - Production experience with retrieval-augmented generation, vector stores, embedding models, chunking, and retrieval improvements. - Experience deploying containerized AI services to cloud environments; Docker, Kubernetes, and infrastructure as code are required areas, with EKS and Terraform preferred. - Ability to explain AI concepts and recommendations to non-technical partners and cross-functional teams. - U.S. citizenship and residence near an approved hub: DC/Maryland/Virginia; Raleigh, Durham, or Chapel Hill; Denver or Colorado Springs; or Dallas/Fort Worth.

Nice to have Experience with enterprise integrations through MCP; AWS AI services such as Bedrock Knowledge Bases or OpenSearch; LLM gateways or model-serving infrastructure; and work in defense, federal, or regulated settings. Familiarity with NIST 800-53, FedRAMP, or NATO D32 is also relevant.

Benefits and work setup Full-time role with flexible remote work near an approved hub. The stated base salary range is $150,000–$160,000, with possible equity awards and discretionary bonuses. Benefits include employer-paid medical, dental, and vision coverage for employees and dependents, a 401(k) contribution, wellness resources, paid time off and federal holidays, parental leave, and home-office and professional-development stipends.