Role Description In this role you will join a team building the backbone of modern defense software delivery — helping ensure warfighters can deploy the latest capabilities rapidly, securely, and reliably. - Embed with strategic customers as a technical partner, working from problem discovery to solution implementation and customer adoption. - Architect, build, deploy, and operate agentic Generative AI systems: APIs, data processing ETL pipelines, integration layers, Retrieval Augmented Generation, and context engineering. - Work in cloud, on-prem, and edge/air-gapped environments to ensure software can run where the mission demands. - Prototype and deploy systems leveraging the core products and design patterns of the Unicorn Delivery Service (UDS); bring back insights from the field for continuous product improvement. - Scope, sequence, and lead delivery of solutions: define living roadmaps, set priorities, trade off speed vs quality vs scope, work across internal teams and customer stakeholders to drive clarity and remove blockers early. - Codify reusable patterns for mission environments: build tools, internal frameworks, playbooks so future deployments are faster, safer, and repeatable. - Act as the technical face to customer leadership: communicate effectively with both technical and non-technical stakeholders, build trust, manage expectations, and ensure successful scale and mission adoption. This is a customer-facing role. - Ability and interest to travel up as needed to client sites, but flexible based on personal preferences. Qualifications - 3+ years of engineering or technical deployment experience (backend or full-stack), ideally in customer-facing or government environments (DoD, intelligence, public sector) or analogous high-assurance contexts. - Strong backend engineering skills: production-grade code in Python or TypeScript; deep familiarity with designing services, APIs, data pipelines, integrations, and backend frameworks. - Familiarity with LLMs or generative AI systems — be able to explain the fundamentals of Context Engineering and understand how model behavior connects to product/mission experience, and how AI capabilities integrate into larger system architectures. - Strong ability to work in ambiguity: define scope, sequence work, make trade-offs between speed, quality, and scope; remove blockers; deliver under pressure in dynamic mission-driven settings. - Excellent communication skills: able to translate complex technical details into clear messaging for non-technical stakeholders; work cross-functionally; build relationships with customers and internal teams. - Mission-oriented mindset. Have an understanding that our work is supporting the defense and freedom of the nation. Requirements - Experience with deploying applications on Kubernetes inside of air-gapped or secure environments. - Experience with Information Retrieval fundamentals including knowledge of keyword and vector based search, document parsing and chunking, document reranking, and SQL/NoSQL search engines. - Experience with developing, executing, and maintaining LLM evaluations. - Experience with open source LLM or SLM models (Llama3, Mixtral, Gemma, Phi) including inference frameworks, structured output, fine-tuning, and model architecture reconfiguration. Benefits - Health: - Medical/Dental/Vision - Premiums are 100% Company Paid - Health Reimbursement Account - Life Insurance - Disability Insurance - Financial: - 401k Retirement Plan - Company Stock Options - Home Office Budget - Leave: - Flexible Time Off (FTO) plus all Federal Holidays, one week for Thanksgiving, and two weeks for Christmas and New Year’s - Paid Parental Leave - Learning: - Reimbursement for approved trainings/subscriptions - Conferences (travel, lodging, and fees)

• You'll build and own the AI systems that make Live Breach feel like a real incident rather than a scripted exercise. • The AI attacker agent - an autonomous LLM-powered agent that receives a threat actor profile, a network briefing, and a configured attack chain, then executes it against a live environment. • The exercise orchestration layer - a parallel system that monitors the network during a live exercise, recognises which attack techniques have executed, listens for correct containment and eradication actions from participants, and surfaces investigation tasks tied to real attacker behaviour. • Prompt engineering for both red and blue team agent components, in close collaboration with our content engineering team • Integration with adversary emulation tooling for realistic technique execution • User emulation and noise generation — simulating realistic background activity so participants must distinguish real attacker behaviour from normal log volume • Documentation and architecture that allows the broader engineering team to operate and debug the AI layer without dependency on any single person.

• Own the architecture and evolution of the shared components, libraries, and platform capabilities the whole AI team builds on. • Design and build the CI/CD patterns, deployment pipelines, observability tooling, and developer workflows that make shipping agents to production predictable and repeatable. • Lead the team on AI tooling adoption—coding assistants, agentic development workflows, evaluation frameworks. • Carry work from requirements shaping and solution design through deployment, monitoring, and iteration. • Articulate a clear engineering direction to your team and to stakeholders. Translate ambiguous problems into concrete plans. • Actively grow the engineers around you. Run technical reviews, establish best practices, and create an environment where the team can move quickly—without constantly second-guessing their decisions.

• Partner with Product to translate roadmap priorities into technical designs, implementation plans, and delivery strategies • Design and implement features across application, data, and infrastructure layers • Own and evolve core platform architecture across both Rails and Python systems • Make high-impact architectural decisions (service boundaries, modularization, data access patterns, scalability) • Build and optimize high-scale background processing systems (notifications, scoring, ingestion, exports, etc.) • Develop workflows spanning APIs, background jobs, ingestion pipelines, search/discovery, and reporting • Investigate production issues, identify root causes, and improve platform reliability • Implement AI-powered features including LLM orchestration, prompt workflows, and observability controls • Leverage AI-assisted development tools for coding, testing, refactoring, and documentation • Document architectural decisions and system behavior for long-term maintainability • Collaborate with Engineering, Product, Customer Success, and Support teams to continuously improve the platform