Senior AI Software Engineer

Who We Are
At Firestorm, we’re on a mission to revolutionize how defense solutions are designed and delivered. Our goal is to empower U.S. ally nations to effectively deter aggressors — regardless of their defense budget — through innovative, cost-efficient technologies. We call this vision “democratized deterrence.” As a VC-backed company at the intersection of defense and Silicon Valley, we’re pioneering the development of mission-adaptable aerial vehicles that put power back into the hands of operators. By prioritizing operator effectiveness, we’re pioneering a new era of aerial vehicle design. We aim to upend the traditional defense procurement model by delivering world-class capabilities at a fraction of the usual cost. Join us at Firestorm as we redefine defense procurement, making cutting-edge technology accessible to all at a fraction of the cost. About the Role At Firestorm, we are building autonomous aerial systems that operate where they are needed most, when they are needed most. Our mission requires speed, ingenuity, and a relentless commitment to engineering excellence. We move fast, test constantly, and deliver capability that performs in the real world, not just in simulation. 
We are looking for a Senior AI Software Engineer who is excited to build, test, and deliver production-grade AI-enabled software systems. This is a hands-on role, working on end-to-end delivery from early prototypes through hardened deployments. You will potentially lead a small team in the future. This role blends strong software engineering fundamentals with modern AI system development: turning ambiguous user intent into reliable, structured outputs; integrating safely with existing internal systems; and building the validation, observability, and governance required for high-integrity environments. This is not a research-only role. You will ship, iterate quickly, and set the technical and execution standard for a team operating under demanding timelines. 
If you want to build systems that matter, own your work end to end, and be part of a team that values bold thinking grounded in rigorous engineering, Firestorm is the place to do it.  What You'll Do

• Lead hands-on development of AI-enabled software systems from concept to deployment, balancing rapid iteration with engineering rigor 
• Support end-to-end delivery across product and engineering concerns: requirements intake, decomposition into structured outputs, validation, and release readiness 
• Build and maintain agentic workflows (tool use, state handling, retries, human-in-the-loop gates) with clear safety and quality constraints 
• Define and enforce structured output contracts (schemas, validations, compatibility expectations) to reduce brittleness and enable long-term evolution 
• Establish build and release discipline: versioning conventions, reproducibility practices, CI quality gates, and rollback-ready releases 
• Drive operational readiness: observability, auditability, failure-mode handling, and secure-by-default service behavior 
• Partner with adjacent engineering teams to integrate with existing platforms without bypassing governance boundaries 
• Set team execution cadence: sprint planning, technical prioritization, code reviews, and operational response expectations 
• Identify high-risk failure modes in AI workflows and ship mitigations (guardrails, validation layers, permissioning, throttling, and safe defaults) 
• Produce clear technical documentation and decision records that enable fast onboarding and consistent engineering behavior 

Minimum Qualifications 

• Bachelor’s degree in Computer Science, Engineering, or related field (or equivalent practical experience) 
• U.S. Citizenship and the ability to obtain and maintain a U.S. Government security clearance 
• 8+ years of experience building and shipping production software systems (services, platforms, or distributed systems) 
• 4+ years of production AI/ML experience, including ownership of real-world reliability, safety, and performance outcomes 
• Demonstrated experience shipping LLM-enabled applications to production (e.g., tool use/function calling, structured outputs, retrieval-augmented generation, robust error handling and fallback strategies) 
• Experience designing AI evaluation and quality gates (offline eval harnesses, regression suites, golden sets, automated grading, CI integration) 
• Experience operating AI systems in production (monitoring, alerting, quality/re