Senior Software Engineer (Formal Methods & Agentic Systems)

Responsibilities

• Take the research-grade formal/agentic system to production: a real package, test suite, service interface, documentation a cold-joiner can use, and a release cadence.
• Own the architecture for reliability, packaging, test coverage, typing, CI, performance, and release discipline of the formal/agentic system.
• Wrap solver runs in agent loops where the agent proposes and the solver disposes, deliberately defining what the agent may touch when a proof fails.
• Model messy client business rules — compliance requirements, rate structures, program eligibility, design constraints — as constraints and shapes that check mechanically, and build the review habit that keeps those models honest.
• Reason over per-customer digital twins, checking proposed changes against the twin's constraints and shapes before anyone touches the real system.
• Define the agent seam: where LLM agents may assist (translation, hypothesis, explanation) and where they're forbidden (anything that asserts).
• Make proof results legible to client stakeholders who will never read a proof — clearly communicating what was checked, against what, and what was not checked.

Core Qualifications

• 5+ years of productionization experience: you've taken someone else's prototype or research code to production, with packaging, tests, CI, observability, and docs, respecting the design you inherited while changing it with evidence.
• Real depth in formal methods — you've built things with SMT/constraint solvers (Z3-class), automated theorem proving, or heuristic search over proof and plan spaces (AO*-class), and can speak to soundness, completeness, and their practical costs.
• Experience with data modeling and shape validation — ontology/taxonomy design, SHACL shapes as data contracts, RDF/OWL/SPARQL, or comparable schema-level validation on knowledge graphs — where you've modeled domains, not just queried them.
• Agentic AI literacy — you've built or wired LLM agents, understand their failure modes, and know exactly why an agent may propose but never assert around formal tooling.
• Strong generalist engineering skills: Python fluency, service design, and the judgment to keep a powerful system simple to use.
• Comfort partnering closely with a principal engineer/inventor — direct, kind candor, with no ego about whose idea wins.
• Practical familiarity with our core stack — Z3/SMT/SAT solvers, constraint programming, SHACL/RDF/OWL/SPARQL, Python 3.12+ (type-strict, FastAPI when needed), and Postgres.
• Experience with test engineering for formal systems — counterexample regression testing, property-based testing — and CI/release discipline for libraries.
• Working knowledge of LLM provider APIs and agent frameworks (or hand-rolled agent loops), even if your primary depth is on the formal-methods side.
• Bachelor's Degree: Master's is a Plus
• Domain experience in Energy, Utilities, Commercial Real-Estate, and Infrastructure is a plus

Why AZX!

Additional Information

Next Steps