Senior Embedded Performance Engineer

Job Title

Senior Embedded Performance Engineer

Role Summary

Work on low-level runtime software that orchestrates compute across Fractile accelerators to maximize throughput and minimize latency for ML inference. You will drive the first accelerator compute runs, run microbenchmarks on silicon, and translate profiling data into actionable hardware and software improvements.

This role sits at the intersection of runtime, firmware, simulation, compiler, and hardware teams and focuses on performance-critical code close to the metal.

Experience Level

Senior — typically 3+ years of relevant industry experience working on embedded or performance-critical software.

Responsibilities

Primary responsibilities include writing, measuring, and improving low-level software to extract real-world performance from accelerator hardware.

• Implement and optimise ML kernels in C and assembly (RISC-V and custom ISA where required).
• Develop low-level control paths: scheduling, synchronization, and data movement feeding those kernels.
• Design and run targeted validation workloads and microbenchmarks to align simulation and silicon behaviour.
• Profile and benchmark software and hardware to identify regressions and quantify improvements.
• Collaborate closely with simulation, hardware, ML, compiler, firmware, and runtime engineers to turn profiling data into architecture and software changes.
• Drive early silicon bring-up and produce reproducible performance measurements.

Requirements

Must-have technical skills and attributes.

• Proven experience in deeply embedded software development and working close to hardware.
• Strong performance instincts: ability to reason about low-level architecture, memory behaviour, and cycle costs.
• Excellent C programming skills and pragmatic approach to maintainable low-level code.
• Comfortable writing and debugging optimized assembly (RISC-V experience is ideal).
• Experience with profiling, benchmarking, and tracking regressions in low-level systems.
• Collaborative, high-ownership mindset with clear communication and a bias for execution.

Nice-to-have:

• Experience with GPUs or dedicated ML accelerators.
• Familiarity with Rust and/or Python.
• Experience with functional or performance simulators and writing validation/benchmark workloads.
• Knowledge of modern ML inference workloads.

Education Requirements

Degree in Computer Science, Electronic Engineering, Mathematics, Physics, or a related field, plus 3+ years of industry experience.

About the Company

Company: Fractile

Headquarters: London, UK

Fractile is on a mission to revolutionize AI by developing silicon, systems, and software that enable the fastest execution of advanced models at lower costs. Established in 2022, the company has rapidly expanded, fostering a collaborative culture in its London and Bristol offices. With a focus on innovation in ML/AI IC product development, Fractile combines hardware and software to deliver high-impact solutions for data center applications.