Member of Technical Staff — Environments / Evals

Axiōma Search; United Kingdom; Remote; GBP 90.000 - 130.000; Vollzeit

Zusammenfassung

Axiōma Search is seeking a driven RL research scientist to advance post-training methods for robotics through scalable, multimodal models. The role focuses on designing and running RL post-training pipelines, leveraging GPU-native simulation environments and cutting-edge diffusion and autoregressive approaches.

You will collaborate with training infra and simulation teams, craft robust reward signals, and push results from simulation to real-world robotic behaviour.

Qualifikationen

• Strong RL research background in large-scale or real-world systems.
• Experience post-training large models using RL methods (RLHF, PPO, etc.).
• Proficiency in Python and PyTorch with distributed training experience.
• Track record from a top AI lab or frontier model team.
• Publications at top-tier venues (NeurIPS, ICML, ICLR, CoRL, RSS).

Aufgaben

• Design and run RL post-training pipelines for large multimodal robotics models across VLA and world model architectures.
• Work with a GPU-native simulation environment to optimize data flow.
• Apply sampling during training (diffusion and autoregressive) to reduce distribution drift.
• Design reward models and feedback signals transferring from simulation to real robotics.
• Iterate on diffusion-based and autoregressive action models using RL where beneficial.
• Collaborate with training infra and simulation teams to ship production-ready systems.
• Run rigorous experiments and translate results into better models, not just benchmarks.

Kenntnisse

RL research

RL post-training

Python & PyTorch

Distributed training

Publications in top venues

Jobbeschreibung

About

Most RL post-training work assumes the environment lives somewhere outside the model. Here, the physics simulator runs natively on GPU – which changes the data flow, the optimisation surface, and what's actually possible. The team is using that to push RL post-training for robotics in directions that aren't available to labs working with standard LLM setups.

This is a well-funded physical AI lab building universal foundation models for general-purpose robots. The research stack spans both VLA models — mapping perception and language to robot actions — and world models that learn and predict environment dynamics. Both are in active development, and RL sits at the centre of how they're advancing both.

The team is small, deeply research-driven, and recruited from top AI labs.

What you'll do

• Design and run RL post-training pipelines for large multimodal robotics models, across both VLA and world model architectures
• Work with a GPU-native simulation environment, enabling data flow optimisations not available in standard LLM RL setups
• Apply sampling during training — across diffusion and autoregressive approaches — to avoid distribution drift
• Design reward models and feedback signals that transfer reliably from simulation to real-world robotic behaviour
• Iterate on both diffusion-based and autoregressive action models, applying RL where it pushes capability furthest
• Collaborate closely with training infra and simulation teams to turn research ideas into production-ready systems
• Run rigorous experiments and translate results into better models, not just better benchmarks

What you'll need

• Strong RL research background, applied to large-scale or real-world systems — LLM-background RL considered if the research track is strong
• Experience post-training large models using RL methods: RLHF, GRPO, PPO, or similar
• Proficiency in Python and PyTorch; experience with large-scale distributed training
• Track record from a top AI lab, frontier model team, or leading robotics or embodied AI group
• Publications at top-tier venues strongly preferred (NeurIPS, ICML, ICLR, CoRL, RSS, or similar)

Optional Bonus

• Experience with diffusion model RL or autoregressive action model training
• Background in sim-to-real transfer or embodied AI
• Familiarity with robotics control or physical data pipelines

Shortlisted candidates will be contacted within 48 hours.