ML Performance Engineer (AI)

Location: London, United Kingdom; hybrid working model with in-person collaboration and remote work.

Company

hirify.global builds an AI platform for autonomous driving, using embodied intelligence and scalable deployment to enable vehicles to learn from real-world experience.

What you will do

• Profile inference performance across model graphs, compiler and runtime behaviour, kernel execution, and memory movement.
• Implement and validate optimisations in compilers, runtimes, and kernels, including fusion, scheduling, quantisation-aware performance, and custom kernels.
• Build benchmarking and regression tests across models, devices, and software releases.
• Optimise ML inference for edge targets including NVIDIA Orin/Thor and Qualcomm platforms.
• Collaborate with model, platform, and deployment engineers on performance trade-offs and deployment-aware decisions.
• Contribute to tooling, documentation, and technical discussions around ML performance.

Requirements

• Experience improving production or production-adjacent systems under latency, memory, bandwidth, power, thermal, or cost constraints.
• Hands-on experience with at least one relevant stack, such as TensorRT, CUDA, Qualcomm QNN, Triton, or OpenCL.
• Ability to work from high-level model behaviour through to kernel- and runtime-level execution.
• Strong software engineering fundamentals in debugging, profiling, testing, and maintainable code.
• Clear communication and effective collaboration across ML, systems, and deployment teams.
• Availability to work in a hybrid setup in London, United Kingdom.

Nice to have

• Experience deploying or benchmarking ML models on embedded or edge devices.
• Familiarity with NVIDIA or Qualcomm SoCs and performance tooling.
• Proficiency in Python and C++.
• Experience supporting other engineers or contributing to technical direction within a small team.

Culture & Benefits

• Hybrid work with core hours, office collaboration, and hands-on work in vehicle workshops and labs.
• Market-benchmarked salaries, meaningful equity, and comprehensive location-dependent benefits.
• Relocation support and visa sponsorship where applicable.
• Learning and development budgets for training, conferences, and professional growth.
• Health insurance, dental coverage, enhanced parental leave, retirement or pension benefits where applicable, therapy access, wellbeing partnerships, and team socials.
• An evolving environment with significant ownership in shaping how the organisation works.

Hiring process

• Initial call or recruiter screen.
• Deep-dive technical interviews covering programming, system design, and domain-specific topics, taking approximately three hours in total.
• Final interview focused on mission and values alignment.