Senior Perception Engineer - Spatial Understanding & Navigation

Humanoid; Greater London; On-site; GBP 100,000 - 125,000; Full time

Job summary

A leading AI and robotics company in the United Kingdom is seeking a Senior Perception Engineer specializing in Spatial Understanding & Navigation. The role involves developing advanced spatial understanding systems, integrating perception models, and collaborating on navigation challenges. Ideal candidates will have deep experience with large models in machine learning, along with expertise in scene understanding and 3D reconstruction. This position provides a competitive salary and an array of attractive benefits including health insurance and stock options.

Benefits

Competitive salary and stock options

Paid vacation

Travel opportunities

Private health insurance

Office perks like free meals

Startup culture

Qualifications

• Deep experience in machine learning for vision or embodied AI.
• Strong background in scene understanding and spatial reasoning.
• Proficiency in PyTorch and large-scale ML systems.

Responsibilities

• Develop spatial understanding systems for robot locomotion.
• Work on open-ended navigation powered by VLA models.
• Design auto-labeling and large-scale data pipelines.
• Implement scene understanding and 3D reconstruction methods.
• Collaborate with cross-functional teams for model integration.
• Evaluate new model architectures and datasets.

Skills

Machine learning for vision

Scene understanding

Spatial reasoning

3D reconstruction

PyTorch

Research skills

Job description

Humanoid is the first AI and robotics company in the UK, creating the world’s most advanced, reliable, commercially scalable, and safe humanoid robots. Our first humanoid robot HMND 01 is a next‑gen labour automation unit, providing highly efficient services across various use cases, starting with industrial applications.

We are looking for the Senior Perception Engineer – Spatial Understanding & Navigation to join our team based in London, UK.

What You'll Do

• Develop next‑generation spatial understanding systems for robot locomotion and manipulation, integrating perception and high‑level reasoning.
• Work on open‑ended navigation powered by Vision‑Language‑Action (VLA) models — enabling robots to understand context, predict intent, and act in complex, dynamic environments.
• Design and scale auto‑labeling and large‑scale data pipelines to train and evaluate multimodal models for navigation and interaction.
• Develop and implement scene understanding and 3D reconstruction methods that give robots persistent spatial memory and geometric awareness.
• Collaborate with cross‑functional research and engineering teams to bring large vision‑language models into real‑world robotic systems.
• Stay ahead of the field — rapidly evaluate new model architectures, benchmarks, and datasets to guide our embodied AI roadmap.

What We're Looking For

• Deep experience in machine learning for vision or embodied AI, ideally with large models (VLMs, VLAs, transformers, diffusion, or multi‑modal architectures).
• Strong background in scene understanding, spatial reasoning, or 3D reconstruction from visual data.
• Proficiency in PyTorch and hands‑on experience building, fine‑tuning, and deploying large‑scale ML systems.
• Strong experimental and research skills — capable of taking projects from concept to model training, evaluation, and robot integration.
• Comfortable working in a fast‑moving, research‑driven environment with evolving models, data, and tools.

What We Offer

• Competitive salary plus participation in our Stock Option Plan
• Paid vacation with adjustments based on your location to comply with local labour laws
• Travel opportunities to our Vancouver and Boston offices
• Private Health Insurance
• Office perks: free breakfasts, lunches, snacks, and regular team events
• Freedom to influence the product and own key initiatives
• Collaboration with top‑tier engineers, researchers, and product experts in AI and robotics
• Startup culture prioritising speed, transparency, and minimal bureaucracy