AI Software Engineer

Role overview

Build and ship production AI agents for workflows used in secure and regulated environments. The role spans agent design, language-model integration, retrieval, evaluation, and cloud deployment, with an emphasis on traceable behavior, measurable quality, and responsible use. You will work with product and engineering partners to turn AI opportunities into maintainable platform capabilities.

Responsibilities - Design reliable agent systems with multi-step orchestration, tool use, and clear traceability. - Build retrieval components, including ingestion, embeddings, chunking, search, reranking, and connections to APIs and knowledge sources. - Create and operate integrations using the Model Context Protocol, including servers and clients. - Deploy and maintain AI research infrastructure using Kubernetes, infrastructure as code, Helm, and GitOps practices. - Develop evaluation and regression suites for groundedness, faithfulness, relevance, and retrieval quality, and run them in CI. - Advise product teams on use-case scope, agent architecture, model choice, and output-quality standards.

Requirements - At least two years of full-time software, machine-learning, or AI engineering experience, including production delivery of language-model systems. - Hands-on experience with tool-using agents and multi-step orchestration frameworks such as LangGraph or LangChain, or equivalent. - Production experience with retrieval-augmented generation, vector stores, embedding models, chunking, and retrieval-quality improvement. - Experience deploying containerized AI services with Docker and Kubernetes, plus infrastructure-as-code tools; EKS and Terraform are preferred. - Ability to explain AI recommendations to non-technical partners and cross-functional teams. - U.S. citizenship and residence in one of these hiring regions: DC/Maryland/Virginia; Raleigh/Durham/Chapel Hill; Denver/Colorado Springs; or Dallas/Fort Worth.

Nice to have - Experience with MCP, enterprise integrations, AWS AI services, LLM gateways, or self-hosted model serving. - Background driving AI adoption, or working with defense, federal, or regulated environments and frameworks such as NIST 800-53 or FedRAMP.

Benefits and work setup - Full-time role with flexible remote work, flexible paid time off, and federal holidays. - Listed benefits include employer-paid medical, dental, and vision coverage, a 401(k) contribution, equity eligibility, home-office and professional-development stipends, wellness resources, and parental leave. - Base salary is listed as $150,000–$160,000; final compensation depends on experience, skills, seniority, and location. Eligibility for discretionary bonuses may also apply.