Software Engineer – RL Environments (3 Openings)

Role responsibilities

Design datasets, evaluation frameworks, and reward signals to improve the training and alignment of next-generation AI models. Collaborate with researchers to build scalable data pipelines and identify model failure modes across various domains.

Requirements

Requires 1-4 years of professional software engineering experience with strong programming skills and a passion for reinforcement learning. Candidates should be able to design experiments and iterate quickly in a fast-paced startup environment.

Key skills

Software Engineering, Reinforcement Learning, Dataset Design, Evaluation Frameworks, RLHF, RLVR, Data Pipelines, Experimental Design, Quantitative Analysis, AI Benchmarking, Problem Solving, Synthetic Data Generation

Keywords

AI, Reinforcement Learning, RLHF, RLVR, Frontier AI Labs, Software Engineering, Data Pipelines, Synthetic Data, AI Safety, AI Benchmarking, Evaluation Rubrics, Reward Signals, Enterprise Workflows, Finance, Startup