M

MatX

Designs high-throughput AI hardware chips

Formal Verification Engineer

Hardware Validation & TestingUpdated on Nov 14
Full-timeMountain View, CA, USA

About the Job

Requirements

  • Hands-on experience with hardware model checking, including writing SVA/PSL properties, running bounded or unbounded proofs, and closing formal verification targets at block or subsystem level.
  • Practical experience with at least one interactive theorem prover, such as Lean, Coq, Isabelle/HOL, or Agda.
  • Ability to work across the hardware/software boundary, understanding RTL microarchitecture and compiler intermediate-representation design well enough to identify important correctness properties.
  • Ability to work in a small team where the scope of ownership is large and may shift quickly.

Responsibilities

  • Apply model checking and formal property verification to RTL blocks, memory subsystems, and interconnects, providing complete coverage wherever possible using tools such as JasperGold or VC-Formal.
  • Develop and maintain machine-checked proofs for critical compiler transformations, ensuring correctness of lowering passes from the high-level programming model down to hardware.
  • Build embeddings of hardware description languages and simulator models into interactive theorem provers such as Lean 4, Rocq, or Isabelle/HOL, and use those embeddings to prove functional correctness and microarchitectural properties against the designs.
  • Collaborate with architecture, compiler, and silicon verification teams to identify correctness properties worth proving and translate them into tractable proof obligations.
  • Drive methodology for integrating formal tools such as JasperGold and SymbiYosys, or equivalent tools, into existing practices.

Desired Qualifications

  • Experience embedding an existing language or intermediate representation into a theorem prover, such as an HDL, compiler intermediate representation, or instruction set architecture.
  • Experience with compiler correctness proofs or verified compilation, such as CompCert-style proofs or translation validation.

About the Company

MatX

Designs high-throughput AI hardware chips

MatX builds high-throughput AI accelerators for large language models. Its main product is a dedicated chip where every transistor is optimized for running large neural networks, aiming to deliver strong performance for training and inference of LLMs. The company also develops the surrounding software stack, including compilers, to make the hardware easy to program for ML engineers (e.g., through JAX-based workflows). Unlike general-purpose processors, MatX focuses on specialization and full-stack optimization from silicon to software. Its goal is to enable organizations with substantial AI workloads to scale efficiently by providing powerful, purpose-built hardware and the compatible software tools they need to deploy and optimize large models.

Company size
51-200
Company stage
Series B
Total funding
$604.9M
Headquarters
Mountain View, CA
Founded
2022

Recently Posted Jobs

Explore more opportunities at MatX

See more jobs