Mercor
Research Engineer Intern - Environments, Data and Post-Training
San Francisco · On-site · Internship · Posted Oct 27, 2026
About the job
Conduct applied AI research and engineering on post-training, data generation, and evaluation systems to improve language models’ tool use, agentic behavior, and real-world reasoning.
What you'll do
- Develop post-training and RLVR pipelines, including reward-shaping experiments and algorithmic improvements.
- Build scalable data generation and augmentation pipelines, and assess data quality and performance uplift.
- Create and operate evaluation systems, benchmarks, rubrics, evaluators, and metrics at scale.
What they ask for
- Strong applied research background focused on post-training and/or model evaluation.
- Strong coding proficiency and hands-on experience with machine learning models.
- Strong understanding of data structures, algorithms, backend systems, and engineering fundamentals.
- Familiarity with APIs, SQL/NoSQL databases, and cloud platforms.
Nice to have
- Industry post-training team experience; publications at top-tier conferences (NeurIPS, ICML, ACL).
- Experience training or evaluating models, synthetic data generation, LLM evaluations, or RL-style workflows; relevant work samples or code repositories.
Pay
$70 per hour (base salary)
Tools
RLVR, GRPO, DAPO, LLM, SQL/NoSQL
AI focus
Post-training and RLVR, reward shaping, synthetic data generation, and large-scale evaluation to improve LLM capabilities.
Model-written summary · the original posting is authoritative