Machine Learning Engineer (Synthetic Data)

Location: Based in the London office, United Kingdom; hybrid working policy with time in the office and from home.

Company

hirify.global develops embodied AI software and foundation models for mapless, hardware-agnostic autonomous driving systems.

What you will do

• Post-train and iterate GAIA-class world models for rig transfer, pose transfer, and conditioning based on geometry, calibration, and actions.
• Own the synthetic-data generation loop from configuration and large-scale GPU inference to training-ready artefacts with clear model and settings lineage.
• Integrate synthetic data into behaviour-cloning, reward-model, and reinforcement-learning training, including binarisation, mix ratios, quality filters, and impact experiments.
• Diagnose geometry, calibration, controllability, novel-view-synthesis, odometry, and camera-layout failures that affect generated video quality.
• Improve inference throughput, valid-generation rates, and self-service workflows using techniques such as distillation, KV caching, shortcut methods, and reduced step counts.
• Expand synthetic-data coverage to new vehicle platforms and safety-critical scenarios such as Emergency Lane Keeping and Automatic Emergency Braking.

Requirements

• 4+ years of applied machine learning or research engineering experience, including training and shipping neural networks.
• Strong Python and PyTorch or equivalent skills, with experience debugging GPU training and reading model code.
• Hands-on experience with video, generative, or world models, including diffusion, flow matching, autoregressive video, novel-view synthesis, or neural rendering.
• Working knowledge of cameras and 3D geometry, including multi-camera rigs, intrinsics, extrinsics, warps, and reprojection.
• Experience taking generated or simulated data into downstream models and measuring impact through mixes, ablations, and failure analysis.
• Experience operating reliable multi-GPU generation or training workflows and large video artefacts at scale.

Nice to have

• Experience with controllable generation, video diffusion or flow models, distillation, few-step sampling, or KV caching.
• Background in autonomous vehicles, robotics, simulation, or multi-sensor driving data.
• Experience with Flyte, Ray, Spark-style jobs, dataset lineage, or training-mix configuration.
• Experience with reward models, offline reinforcement learning, closed-loop driving-policy evaluation, cloud GPU fleets, or distributed training.

Culture & Benefits

• Hybrid work combining office and home working, with core working hours and flexibility to determine the schedule with the team.
• High-trust, high-autonomy environment focused on generative simulation and real-world autonomous-driving impact.
• Inclusive and collaborative culture with close work across machine-learning research, infrastructure, and driving-model teams.
• Opportunity to work with GAIA-scale video generation, camera transfer, pose control, and vehicle-training infrastructure.

Hiring process

• hirify.global provides an inclusive interview experience and can accommodate candidates who require adjustments.
• Application materials may be used to pre-fill the application form.