F

Fractile

Specialized AI inference chips and software

Senior Embedded Performance Engineer

Embedded EngineeringConfirmed live in the last 24 hours
Full-timeIn-person

About the Job

Requirements

  • Proven deeply embedded software experience.
  • Strong performance instincts, including the ability to reason about low-level architecture, memory behaviour, and where cycles are spent.
  • Excellent C skills and a pragmatic approach to building high-quality, maintainable low-level code.
  • Comfort writing and debugging optimised assembly; RISC-V is ideal.
  • A degree in Computer Science, Electronic Engineering, Maths, Physics, or a related field, and 3+ years of industry experience.
  • Experience with GPUs or dedicated ML accelerators is desirable.
  • Rust and/or Python experience is desirable.
  • Experience with simulators, functional or performance, and writing validation or benchmarking workloads is desirable.
  • Familiarity with modern ML inference workloads is desirable.

Responsibilities

  • Write and optimise performance-critical machine-learning kernels in C, using assembly where it matters, including RISC-V and the company's own instruction set architecture.
  • Build low-level control paths that feed kernels, including scheduling, synchronisation, and data movement.
  • Write targeted validation workloads and microbenchmarks to keep simulation and hardware behaviour aligned and performance measurable.
  • Profile, benchmark, and track regressions so performance improvements are real and repeatable.
  • Work closely with simulation, hardware, machine-learning, compiler, firmware, and runtime engineers, using profiling data to provide architecture feedback and improve performance.
  • Drive the first accelerator compute runs, evaluate performance on silicon, run early benchmarks, and feed results back into the hardware and software roadmap.

Desired Qualifications

  • Experience with GPUs or dedicated ML accelerators.
  • Rust and/or Python experience.
  • Experience with simulators, functional or performance, and writing validation or benchmarking workloads.
  • Familiarity with modern ML inference workloads.

About the Company

Fractile

Specialized AI inference chips and software

Fractile designs specialised AI inference chips, systems, and software to run very large AI models. Its approach packs DRAM directly on top of logic to boost memory bandwidth and capacity, offering an alternative to HBM and SRAM-based designs. The company operates full-stack across research, hardware, software, and systems, delivering an integrated hardware-software stack. Its goal is to enable scalable, high-performance model inference by meeting demanding memory needs with a complete solution.

Company size
51-200
Company stage
Series C
Total funding
$984.1M
Headquarters
London, United Kingdom
Founded
2022

Recently Posted Jobs

Explore more opportunities at Fractile

See more jobs