Applied AI Engineer: RL Environments & Evaluation

Aptura; Greater London; On-site; GBP 90,000 - 130,000; Full time

Job summary

Aptura in London seeks a Member of Technical Staff for Applied AI to build tasks and environments used to evaluate agents in finance, healthcare, and legal domains. You will construct RL environments around real-world spreadsheets, documents, and workflows, write verification logic and reward signals, and collaborate with domain experts to define what constitutes a correct answer for real-world models.

This role blends engineering and research, with ownership of end-to-end ground truth

Qualifications

• Experience building with LLMs for evaluation and benchmarking.
• Design tasks with golden answers, rubrics, and programmatic rewards.
• Proactive, high-agency engineer who thrives in a small team.
• Translate complex domain workflows into structured tasks for models.

Responsibilities

• Build RL environments across finance, healthcare, and legal domains
• Assist in designing tasks with golden answers, calibrated rubrics, and programmatic reward signals
• Write verification logic and reward functions that can distinguish good model outputs from bad ones
• Work directly with domain experts (investment analysts, physicians, attorneys) to translate complex professional workflows into structured tasks
• Prototype new approaches to evaluation, verification, and synthetic data generation

Skills

LLMs prompting

Evaluation design

Agentic harnesses

Tools

AWS

GCP

Job description

Aptura in London seeks a Member of Technical Staff for Applied AI to build tasks and environments used to evaluate agents in finance, healthcare, and legal domains. You will construct RL environments around real-world spreadsheets, documents, and workflows, write verification logic and reward signals, and collaborate with domain experts to define what constitutes a correct answer for real-world models.

This role blends engineering and research, with ownership of end-to-end ground truth