High-Performance Robotics ML Engineer (London)

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

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.