Research Engineer (RL Environment)

Research Engineer (RL Environment)AboutAgents do not improve in a vacuum. They need environments to operate in, tasks to solve, and clear signals for what good looks like. This role exists to build that layer.This is a VC-backed challenger lab building state-of-the-art computer-use agents.Recent progress has made performance highly competitive on computer-use style benchmarks, and the company has launched a more visible product layer to make the technology easier to demonstrate.The team you'd be joining builds the playground itself: synthetic websites, structured workflows, task sets, and evaluation environments where agents can act, fail, retry, and learn.What you’ll doBuild training and evaluation environments for agentic systemsCreate synthetic websites, workflows, and task suites that reflect useful real-world workDefine reward signals and success criteria for agent behaviour in structured environmentsTurn documentation, tools, and existing workflows into interactive agent tasksImprove the realism, coverage, and difficulty of training environments over timePartner with research teams to convert product failures into better environments and tasksBuild internal tooling to generate, run, and measure large task sets reliablyWhat you’ll needStrong software engineering skills, ideally in Python plus web or backend systemsExperience with RL, reward design, or synthetic data generationExperience building internal tools, simulations, evaluation systems, or synthetic environmentsAbility to structure ambiguous workflows into clear tasks with measurable outcomesGood product instinct for what makes an environment realistic and useful for agentsComfort working at the intersection of engineering, research, and experimentationHigh ownership and a practical mindsetShortlisted candidates will be contacted within 48 hours.