Skip to main content
TALENT247 // SPECIALIST AI EXECUTIVE SEARCH & TECHNICAL RECRUITMENT
ROB · Robotics & Embodied AI

Senior 3D Perception & Sensor Fusion ML Engineer

Oxford, UK · Full-time · Hybrid

AI Specialism

Robotics & Embodied AI

Workplace

Hybrid

Location

Oxford, UK

Compensation

£85k – £120k

annual package

Role Dossier & Specification

REF: SENIOR-3D-PERCEPTI

THE CLIENT & MANDATE

Our client is an Oxford-headquartered autonomous vehicle software leader commercializing universal, safety-certified autonomy across industrial logistics yards, airports, ports, mines, and commercial passenger shuttles. Unlike fair-weather highway demos, their fleets operate 24/7 in complex, dynamic industrial environments alongside heavy machinery and pedestrians under heavy rain, fog, dust, and night-time conditions.

They have partnered with Talent247 to hire a Senior 3D Perception & Sensor Fusion ML Engineer in Oxford. Joining their Core Perception squad, the appointed engineer will design, train, and deploy multi-modal 3D bird's-eye-view (BEV) detection, 4D occupancy, and multi-object tracking networks fusing camera, LiDAR, and imaging-radar streams onto onboard vehicle compute.

KEY RESPONSIBILITIES

  • Architect and train spatiotemporal multi-sensor fusion models (BEV transformers, 4D semantic occupancy networks, point-cloud + image fusion) delivering centimetre-accurate 3D understanding in unstructured and adverse-weather environments.
  • Design self-supervised pre-training, auto-labeling teacher distillation, and active-learning loops over terabytes of multi-fleet driving logs to slash manual 3D cuboid annotation costs.
  • Optimize onboard model architectures via quantization-aware training (INT8/FP16), structured pruning, and TensorRT/C++ graph compilation to hit strict real-time latency and determinism budgets on vehicle GPUs.
  • Build granular safety-critical evaluation slices targeting occluded pedestrians, degraded sensor dropouts, calibration perturbations, and rare industrial obstacles.
  • Collaborate closely with sensor-calibration, motion-planning, and onboard systems engineers from lab hardware-in-the-loop rigs through live test-track and customer fleet rollouts.
  • Mentor fellow perception engineers and contribute to architectural roadmaps across next-generation sensor suites.

TECHNICAL ENVIRONMENT & OFFERING

Their perception stack runs on Python, PyTorch, C++17/20, CUDA/TensorRT, ROS2/custom deterministic middleware, and cloud GPU training clusters. Based hybrid in Oxford, our client offers £85,000–£120,000 GBP base salary plus equity options, generous UK pension, 28 days holiday + bank holidays, private healthcare, and UK Skilled Worker visa sponsorship.

Core Requirements

ESSENTIAL QUALIFICATIONS

  • 5+ years of industry experience in 3D computer vision and deep learning perception for autonomous vehicles, mobile robotics, or embodied AI.
  • Deep hands-on proficiency in PyTorch for training 3D object detection, segmentation, occupancy, or multi-object tracking networks across LiDAR, camera, and/or radar modalities.
  • Solid C++ and CUDA/TensorRT skills for optimizing and integrating trained perception models into real-time onboard vehicle pipelines.
  • Strong geometric fundamentals in camera projection models, extrinsic/intrinsic sensor calibration, ego-motion compensation, and temporal fusion.
  • Proven ability to diagnose real-world fleet failure modes and translate them into measurable model and dataset improvements.

PREFERRED / BONUS EXPERIENCE

  • MSc or PhD in Robotics, Computer Vision, or Machine Learning, or publications at CVPR, ICCV, ECCV, ICRA, or IROS.
  • Experience with foundation vision backbones, distillation from offboard 3D auto-labelers, or safety-critical ISO 26262 / SOTIF validation workflows.

Position Telemetry

Location Oxford, UK (Hybrid)
Department Robotics & Embodied AI
Employment type Full-time
Workplace type Hybrid
Salary range
£85k – £120k annual package