Senior AI Software Engineer

Firestorm

5d•Remote

About The Position

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 Lead 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.

Requirements

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/regression tracking, latency/cost controls, incident response)
Strong proficiency in Python and at least one backend/systems language (e.g., Go, Java, C++, Rust)
Experience designing and evolving structured interfaces (schemas, validation, versioning, migrations, compatibility)
Experience implementing safety/security controls for AI systems (authZ, auditability, data handling boundaries, prompt-injection/abuse mitigation, least-privilege tool access)
Proven ability to lead execution in a fast-paced environment while staying highly hands-on
Excellent communication and documentation skills

Nice To Haves

Experience with LLM evaluation techniques (LLM-as-judge, rubric-based scoring, pairwise comparisons, calibrated metrics, red-teaming)
Experience building agent frameworks (planning, tool routing, state machines, multi-step workflows, fallback strategies, HITL approvals)
Experience with model adaptation (prompt optimization, fine-tuning, adapters/LoRA) and the tradeoffs between prompting vs tuning
Experience with multimodal AI (vision + language) and/or integrating AI with real-time systems
Experience with AI security (prompt injection defenses, tool sandboxing, data exfiltration prevention, policy enforcement)
Familiarity with software supply chain practices (dependency hygiene, artifact provenance concepts, secure release workflows)
Experience working on safety- or mission-critical systems where correctness, traceability, and auditable behavior matter

Responsibilities

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

Benefits

We offer comprehensive medical, dental, and visions plans
401(k) Retirement Savings Plan to invest in your long-term retirement goals
Equity grants for new hires
Unlimited PTO
Extremely generous company holiday calendar, including a holiday hiatus in November, & December
Generous Parental Leave
Lifestyle Spending Account
FSA
DCFSA
HSA
Hospital Indemnity insurance
Critical Illness insurance
Accident insurance
Basic Life/AD&D, short-term and long-term disability insurance, 100% covered by Firestorm. Plus, the option to purchase additional life insurance for you and your family
Mental Health Resources: We provide free mental health resources 24/7 including therapy and more. Additional work-life services, such as free legal and financial support, are available to you as well