Staff ML Engineer: RL for Realistic Simulations

Few&Far; Greater London; On-site; GBP 225,000 - 275,000; Full time

Benefits offered by this job

Equity

Job summary

Few&Far in London is hiring a Member of Technical Staff to own post-training and RL, turning research ideas into models that simulate environments more realistically for testing decisions before deployment.

You will build post-training pipelines (SFT, preference tuning, RL), design reward signals and environments, and create evaluators to prove improvements and ship results into production.

Qualifications

• Hands-on post-training experience on real models (GRPO, PPO, DPO, LoRA or similar).
• Experience building RL environments, reward models or evals, not just running training scripts.
• Strong engineering fundamentals: you can scale training and keep it reproducible.

Responsibilities

• Build post-training pipelines (SFT, preference tuning, RL) that make models behave more realistically in simulation.
• Design reward signals and environments for RL, and define what "realistic" means in measurable terms.
• Build evals that prove a trained model beats the frontier baseline on the tasks that matter.
• Run experiments fast, interpret results honestly and ship what works into production.
• Help set the research and engineering direction as the team grows.

Skills

Post-training experience

RL environments design

Reward models / evals

Engineering fundamentals

Handling ambiguity

Tools

GRPO

PPO

DPO

LoRA

Job description

Few&Far in London is hiring a Member of Technical Staff to own post-training and RL, turning research ideas into models that simulate environments more realistically for testing decisions before deployment.

You will build post-training pipelines (SFT, preference tuning, RL), design reward signals and environments, and create evaluators to prove improvements and ship results into production.