Neural Network Performance Engineer (AI)

TL;DR

Neural Network Performance Engineer (AI): Optimizing neural-network control policies for commercially scalable hirify.global robots with an accent on low-latency inference, hardware acceleration, and smooth real-time motion. Focus on profiling model bottlenecks, implementing custom kernels, adapting models to new hardware, and quantizing or redesigning architectures without sacrificing capability.

Location: On-site in London, UK

Company

hirify.global develops commercially scalable and safe hirify.global robots for industrial applications, including the HMND-01 Alpha platform.

What you will do

• Analyze model architectures to identify performance bottlenecks and define optimization opportunities.
• Optimize neural-network inference for cloud hardware and onboard robot hardware such as NVIDIA Thor.
• Implement custom kernels to reduce memory throughput requirements and inference latency.
• Quantize models while preserving output quality and control capabilities.
• Propose and implement architecture changes that improve performance without sacrificing model capabilities.
• Collaborate with robotics, research, and engineering specialists to deliver responsive robot motion and control.

Requirements

• 3+ years of experience building deep-learning systems in industry or research, with shipped models or published artifacts.
• At least 1 year of experience optimizing neural-network inference, including bottleneck analysis, custom kernels, model quantization, and deep-learning compilers.
• Excellent understanding of GPU architecture and the factors influencing model performance.
• Strong Python and PyTorch or JAX skills, including profiling, numerical debugging, and maintainable research code.
• Ability to document experiments clearly and communicate technical trade-offs precisely.
• Availability for on-site work in London, UK.

Nice to have

• Robotics or autonomous-driving experience.
• Open-source code demonstrating inference-performance improvements.
• Publications at ICLR, ICML, NeurIPS, or equivalent open-source contributions.
• Familiarity with vision-language or vision-language-action models.

Culture & Benefits

• Competitive equity through stock options.
• 30+ paid days off, including annual leave, UK bank holidays, and company closure days.
• Private healthcare with virtual and in-person care.
• Pension scheme with an 8% total contribution on full earnings.
• Daily breakfast, catered lunch, and snacks provided in the office.
• Work alongside engineers, researchers, and product experts developing AI-powered hirify.global robotics.