Senior Software Engineer (Compiler & AI Tooling)

About Code Metal

• Code Metal is the leader in automated software engineering you can trust. As AI writes more of the world's code, the bottleneck in software has shifted from writing code to verifying it works, and AI cannot verify its own work with certainty. Code Metal takes a fundamentally different approach: constrain AI to what it does reliably, verify every step independently of the model using formal methods, and keep engineers in the loop on the decisions that matter. The result isn't code that probably works — it's code that is provably correct, with auditable proof. Customers including the U.S. Air Force, L3Harris, RTX, and Toshiba use Code Metal to modernize legacy code, optimize performance on real hardware, and move prototypes to production, fast. Founded in 2023 with offices in Boston and San Francisco, Code Metal is funded by Accel, Salesforce Ventures, B Capital, Smith Point Capital, J2 Ventures, Shield Capital, Overmatch, RTX, and others.
• Learn more at codemetal.ai .

The Role

We are looking for an experienced software engineer to help us build a new generation of transpilation tools enabled by AI and modern verification techniques — bridging the gap between algorithm development and deployment to embedded systems.

In this role you will lead the architecture and implementation of novel code generation pipelines that combine Generative AI, Static Analysis, and Formal Verification to translate code written in one language to another. We are open to two distinct backgrounds for this role:

Path A — Compiler / Tooling

You have built a compiler, interpreter, or substantial build tooling (e.g. a Cargo-like build system, a Clang plugin, an LLVM pass, a transpiler). You understand ASTs, IR design, and the full compilation pipeline.

Path B — AI Agentic Product

You have shipped a production AI agentic system — orchestrating LLMs with tool use, state machines, retrieval, or multi-step reasoning pipelines. You know where these systems break and how to make them reliable.

If you fit either profile and are excited by the intersection of AI and systems programming, we want to talk.

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.

Required 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.

Plus one of the following

Compiler/tooling background:

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.

AI agentic product background:

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).

Preferred Requirements

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).

Benefits

Pay depends on experience, but we strive to be at the upper end of the salary range

Health care plan with 100% premium coverage, including medical, dental, and vision

401k with 5% matching

Paid Time Off (uncapped vacation, plus sick and public holidays)

Flexible hybrid or remote work arrangement

Relocation assistance for qualifying employees

Wage Transparency - The salary range for this role is not a guarantee of compensation or salary, as the final offer amount may vary based on factors including, but not limited to, individual proficiency, skills, experience, and location.

We are an equal opportunity employer. US Citizenship may be required for certain project assignments involving security clearance.

Pursuant to the San Francisco Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.