Code Metal is redefining code translation for mission-critical industries, helping partners move more quickly and reliably from algorithm to silicon. The role involves leading the architecture and implementation of novel code generation pipelines that combine Generative AI, Static Analysis, and Formal Verification.
Responsibilities:
- Define software architecture for Agentic AI pipelines — including state machines, orchestration layers, and LLM-integrated workflows
- Build well-tested, extensible code foundations for code translation products, with a focus on correctness and maintainability
- Collaborate with domain specialists to incorporate formal verification and static analysis methods into the code generation pipeline
- Partner with software engineering and research teams to build robust code repositories and CI/CD processes
- Architect and implement complex workflows spanning code parsing, semantic analysis, AI-assisted generation, and output validation
Requirements:
- 7+ years of collaborative enterprise-level software development in C++ or Python, delivering products to a large customer base
- Demonstrated experience gathering requirements from stakeholders and translating them into software designs
- Track record of planning and executing large projects in a team-based setting
- Strong software delivery fundamentals: code review, testing, CI/CD, release management, and build systems
- Hands-on experience building a compiler, transpiler, or substantial build tooling (e.g. a Cargo-equivalent, a custom linker, a language runtime)
- Deep familiarity with compiler infrastructure — Clang, LLVM, MLIR, or equivalent
- Understanding of parsing, AST design, IR transformations, and code generation backends
- Shipped production AI agentic systems — LLM orchestration, tool-use pipelines, multi-step reasoning, or autonomous code generation
- Experience building reliable, observable AI workflows with structured outputs, retry logic, and evaluation frameworks
- Familiarity with ML tools and frameworks (PyTorch, Hugging Face, LangChain, or similar)
- Experience with advanced software verification techniques such as fuzzing, symbolic execution, or formal verification (e.g. TLA+, Coq, Z3)
- Hands-on experience with embedded, heterogeneous (FPGA and/or GPU), or distributed systems
- Familiarity with DSP, RF, communications, or other compute-intensive domains
- Experience optimizing and deploying software on constrained or specialized hardware
- Current security clearance, or ability to obtain one (US Citizenship required for cleared work)