Job details
About this role
Role overview This senior engineering role embeds directly with defense and national security customers as a trusted technical partner, owning AI-enabled solutions end to end, from problem discovery through production deployment. The focus is delivery and applied engineering rather than research: building backend systems, data pipelines, and retrieval layers that power generative AI on a cloud-native platform, then operating those systems across cloud, on-prem, and air-gapped environments.
Responsibilities - Embed with strategic clients to drive solution delivery from discovery through adoption, acting as the on-site technical lead - Architect and ship backend services that power generative AI, including APIs, data pipelines, integration layers, retrieval-augmented generation (RAG), and context engineering patterns - Deploy and operate systems across cloud, on-prem, and air-gapped environments using the core platform and established delivery patterns - Scope and sequence work: define roadmaps, set priorities, navigate speed/quality/scope tradeoffs, and clear blockers across internal teams and customer stakeholders - Codify reusable playbooks, tooling, and internal frameworks so future mission deployments move faster and more repeatably - Translate complex technical work for non-technical customer leadership, build trust, and carry field insights back to product and engineering to improve the platform
Requirements - 4+ years of backend or full-stack engineering experience with production-grade Python - Hands-on design and operation of data pipelines, APIs, and integration layers in production - Experience with information retrieval systems such as keyword search, vector search, document parsing and chunking, reranking, or search engine internals (Elasticsearch, OpenSearch, or similar) - Working knowledge of RAG patterns or applied generative AI, connecting LLMs to real data sources in production - Background deploying or operating software in government, defense, or similarly regulated environments - U.S. citizenship and eligibility to obtain a U.S. security clearance
Nice to have - Kubernetes experience in air-gapped or classified environments - Familiarity with open-source LLMs or SLMs (e.g., Llama, Mixtral, Gemma, Phi), including inference frameworks, structured output, or fine-tuning - Building or maintaining LLM evaluation frameworks - Document processing pipelines at scale (parsing, chunking, embedding, indexing) - Active security clearance (Secret or above) - Prior customer-facing or forward-deployed engineering experience
Benefits and work setup - Remote within the United States with up to 25% travel, flexible based on engagement needs - Salary range $148,750–$201,250 USD, calibrated against national benchmarks - 100% company-paid medical, dental, and vision premiums, plus HSA, life, and disability coverage - 401(k) retirement plan, company stock options, and a home office budget - Flexible time off plus federal holidays and seasonal company closures, with paid parental leave - Reimbursement for approved trainings, subscriptions, and conferences