Neural Network Performance Engineer

Humanoid; Greater London; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Stock options

30+ days paid leave (UK)

Private healthcare

Pension scheme with employer/employee

Free daily breakfast and snacks

Collaborative team environment

Direct access to founding leadership

Job summary

Humanoid in London is hiring a Neural Network Performance Engineer to join the VLA team. You will work on neural-network based control policies with high throughput and minimal latency, on cloud and onboard.

The role focuses on performance bottlenecks, kernel development, and model quantization to ensure smooth robotics operations. The ideal candidate has 3+ years in deep-learning systems, 1+ year in inference performance, and strong Python with PyTorch/JAX skills.

Qualifications

• 3+ years building deep-learning systems with shipped models.
• 1+ years performance of neural network inference.
• Strong understanding of GPU architecture.

Responsibilities

• Analyze performance bottlenecks of a model and suggest improvements.
• Deploy models on cloud or onboard hardware with low latency.
• Implement custom kernels to reduce memory throughput where it matters.
• Quantize models with minimal quality loss.
• Suggest architecture changes to boost performance without losing capabilities.

Skills

Python

PyTorch

JAX

Profiling

GPU architecture

Deep learning

Research coding

Tools

CUDA

Job description

Here at Humanoid, we believe in a future where robots amplify human potential. That’s why we’ve set out on a mission to build the world’s most capable, commercially-scalable, and safe humanoid robots. We’re bringing that mission to life with HMND-01 Alpha - our rapidly developed humanoid platform now running in real industrial pilots - and we’re growing the team to take it even further.

About the Role

We're hiring a Neural Network Performance Engineer to join our VLA team based in London. In this role, you will work on all aspects of running capable neural-network based control policies at a high rate with minimal latency, both on cloud hardware and onboard. Your work will be critical to delivering smooth robot motions while reacting to environment changes as quickly as possible.

What You'll Do

• Analyze performance bottlenecks of a particular model architecture and come up with potential improvements.

• Make the model run on a new hardware (e.g. NVIDIA Thor) efficiently.

• Implement custom kernels to reduce memory throughput requirements where it matters.

• Quantize a model with minimal loss of quality.

• Suggest and implement changes of model architecture that will enable better performance characteristics without sacrificing model capabilities.

What We're Looking For

• 3+ years building deep-learning systems (industry or research) with shipped models or published artifacts to show for it.

• 1+ years experience working on performance of neural network inference (analyzing bottlenecks, writing custom kernels, quantizing models, fighting deep learning compilers).

• Excellent understanding of GPU architecture and why some models run faster than others.

• Strong Python + PyTorch/JAX; you can profile, debug numerics, and write maintainable research code.

• You document experiments clearly and communicate trade‑offs crisply.

• Nice to have:

• Robotics or autonomous driving experience.

• Open source code showcasing your ability to improve inference performance.

• Publications at ICLR/ICML/NeurIPS or equivalent open‑source contributions.

• Familiarity with vision-language (VLM) or vision-language-action (VLA) models.

What We Offer

• Competitive equity: stock options with meaningful upside as we scale.

• 30+ paid days off, including 23 days of annual leave, all UK bank holidays, and additional company closure days (including Christmas-NewYear shutdown).

• Private healthcare, including virtual and in-person care.

• Pension scheme with 8% total contribution (5% employee, 3% employer) on full earnings.

• Free daily breakfast, catered lunch, and snacks in-office.

• Work at the frontier - collaborate daily with world-class engineers, researchers, and product experts building the next generation of AI and humanoid robotics.

• Real ownership - direct access to founding leadership, meaningful input on product direction, and the ability to drive key initiatives from day one.