AI Software Engineer

This is a fully remote position, open to applicants in Colorado, +4 more states.

📋 Description

• Design and implement production-level agentic AI systems using LangGraph and LangChain, with an emphasis on dependability, traceability, and quantifiable output quality.

• Develop agent components such as ingestion pipelines, embedding strategies, chunking, retrieval, and re-ranking.

• Create tool suites that span managed knowledge-base services, vector databases, and both internal and external APIs.

• Integrate agents with corporate tools and knowledge via Model Context Protocol, constructing MCP servers and client consumers.

• Set up and manage cloud infrastructure for R&D AI systems utilizing Amazon EKS, Terraform, Helm, and GitOps delivery methodologies.

• Evaluate agent and LLM output quality through assessment and regression suites focusing on groundedness, faithfulness, relevance, and retrieval quality, executing these in CI.

• Collaborate with Product teams to identify high-impact AI opportunities throughout workflows.

• Provide guidance on agent design, model selection, implementation, responsible AI governance, and output quality standards.

• Create documentation and reusable components that enhance the organization's AI capabilities.

• Convert research-grade AI systems into operational products for national security and regulated networks.

⛳️ Requirements

• A minimum of 2 years of full-time experience in software, ML, or AI engineering with practical production work in building and deploying LLM-based systems.

• Direct experience in developing agentic AI systems featuring tool-calling agents and multi-step orchestration using LangGraph, LangChain, or similar technologies.

• Practical experience with Retrieval-Augmented Generation, including vector stores, embedding models, chunking strategies, and optimizing retrieval quality.

• Experience in deploying containerized AI services to cloud platforms using Docker, Kubernetes (EKS preferred), and infrastructure as code (Terraform preferred).

• Proven ability to convey AI concepts and suggestions to non-technical stakeholders and cross-functional teams.

• U.S. citizenship and residence in an approved hiring location: DC/Maryland/Virginia; Raleigh/Durham/Chapel Hill, NC; Denver/Colorado Springs, CO; or Dallas/Fort Worth, TX.

• Preferred: experience in building MCP servers or clients, or integrating agents with enterprise tools and knowledge bases.

• Preferred: familiarity with AWS AI services such as Bedrock Knowledge Bases, AgentCore, and OpenSearch.

• Preferred: experience managing LLM gateways or serving infrastructure like LiteLLM, vLLM, and GPU-backed self-hosted models, including both single- and multi-tenant configurations.

• Preferred: experience promoting AI adoption within a product organization.

• Preferred: background in or collaboration with the Department of Defense, federal agencies, or regulated environments.

• Preferred: knowledge of NIST 800-53, FedRAMP, or NATO D32.

• Must be eligible to work in the United States; the application will inquire if the candidate currently holds a security clearance.

🏝️ Benefits

• Potential eligibility for equity awards.

• Discretionary bonuses.

• 100% employer-covered medical, dental, and vision insurance for you and your dependents.

• 401(k) plan with a 3% company contribution.

• Extensive wellness benefits, including a One Medical membership, mental health resources, family planning support, and more.

• Equity incentive program.

• Technology and home office stipend for new hires.

• Annual professional development stipend.

• Flexible paid time off, in addition to all federal holidays.

• Generous parental leave policy.

• Flexible remote working options.

• Employee referral bonus program.