Staff ML Performance Engineer (Inference Optimisation)

TL;DR

Staff ML Performance Engineer (Inference Optimisation): Optimising ML inference for edge accelerators and GPUs to enable production-ready autonomous driving systems with an accent on large transformer-based models on low-power devices. Focus on profiling the full inference stack, implementing custom kernels, and ensuring reliability on in-vehicle compute.

Location: Hybrid (London, UK)

Company

hirify.global is a leading developer of Embodied AI technology creating mapless and hardware-agnostic AI products for autonomous driving.

What you will do

• Profile and eliminate bottlenecks across the full inference stack, including model graphs and kernel execution.
• Implement optimizations in compilers, runtimes, and kernels, such as operator fusion and quantization.
• Develop benchmarking and regression testing frameworks to validate performance across different devices.
• Optimize targets for NVIDIA Orin/Thor and Qualcomm platforms.
• Collaborate with model developers to align architecture and training with on-device performance needs.
• Define technical roadmaps and elevate performance engineering standards across the organization.

Requirements

• Proven experience improving performance in production systems with strict latency, memory, and power constraints.
• Proficiency with toolchains such as TensorRT, CUDA, Qualcomm QNN, Triton, or OpenCL.
• Ability to work across levels of abstraction, from high-level model behavior to low-level kernel execution.
• Strong software engineering fundamentals in debugging, profiling, and writing maintainable code.
• Must be based in or able to work from the London office (Hybrid).

Nice to have

• Experience with embedded/edge deployment and benchmarking on real hardware.
• Expertise with NVIDIA and Qualcomm SoCs and their performance tools.
• Proficiency in Python and C++.
• Experience mentoring engineers or driving technical direction in fast-paced teams.

Culture & Benefits

• Hybrid working policy combining office collaboration with home-based work.
• Inclusive and diverse work environment that values new perspectives.
• Opportunity to work on groundbreaking Embodied AI for autonomous vehicles.
• Fast-paced environment focused on solving complex, high-impact problems.