Research Engineer Intern - Environments, Data and Post-Training
Core
Build scalable systems for post-training, RLVR, and synthetic data generation to improve frontier language models' tool use and reasoning.
Role type
Research Engineer (Post-Training & Evaluation)
Builds
Post-training pipelines, reward-shaping experiments, data augmentation systems, and LLM evaluation benchmarks.
Domain
Artificial Intelligence / Large Language Models / Reinforcement Learning
Deliverable
production ML models
Required skills
Applied AI research, post-training workflows, RLVR, machine learning model development, data structures, algorithms, backend systems, API integration, SQL/NoSQL, cloud platforms, experimental design, rubric creation.
Preferred skills
Industry post-training experience, top-tier conference publications, synthetic data generation, RL-style workflows.
Technologies
GRPO, DAPO, LLMs, Cloud platforms, SQL/NoSQL
Responsibilities
Design and run reward-shaping experiments; build data generation and augmentation pipelines; create and refine rubrics and evaluators; operate LLM evaluation systems and benchmarks; quantify data usability and performance uplift.
Seniority
Intern
