Research Engineer Intern - Environments, Data and Post-Training
Mercor · San Francisco
About this role
## About Mercor Mercor’s mission is to organize human intelligence to power the AI economy. We’re a leading AI data company building the layer between human expertise and frontier models—where millions of domain experts are paid to train frontier AI models. Mercor is a profitable Series C company valued at $10B. We work **in-person five days a week** in our **San Francisco, NYC, or London** offices. ## About the Role As a **Research Engineer Intern (Environments, Data and Post-Training)**, you’ll work at the intersection of engineering and applied AI research. You’ll contribute to **post-training and RLVR**, **synthetic data generation**, and **large-scale evaluation workflows** that improve frontier language models. Your work will help train models to master **tool use**, **agentic behavior**, and **real-world reasoning** in production environments. You’ll shape rewards, run post-training experiments, and build scalable systems that improve model performance. ## What You’ll Do - Build and improve **post-training and RLVR pipelines** to understand how datasets, rewards, and training strategies affect performance. - Design and run **reward-shaping experiments** and algorithmic improvements (e.g., **GRPO**, **DAPO**) to enhance tool-use, agentic behavior, and real-world reasoning. - Quantify **data usability, quality, and benchmark performance uplift**. - Create and maintain **data generation and augmentation pipelines** that scale with training needs. - Develop and refine **rubrics, evaluators, and scoring frameworks** to guide training and evaluation. - Build and operate **LLM evaluation systems, benchmarks, and metrics** at scale. - Collaborate with AI researchers, applied AI teams, and experts producing training data. - Thrive in a fast-paced experimental environment with rapid iteration and high ownership. ## What We’re Looking For - Strong applied research background, especially in **post-training and/or model evaluation**. - Strong coding proficiency and hands-on experience with **machine learning models**. - Solid understanding of **data structures, algorithms, backend systems**, and core engineering fundamentals. - Familiarity with **APIs**, **SQL/NoSQL databases**, and **cloud platforms**. - Ability to deeply reason about **model behavior**, **experimental results**, and **data quality**. - Excitement to work **in-person** in **San Francisco** (five days/week; optional remote Saturdays) in a high-intensity, high-ownership environment. ## Nice to Have - Real-world **post-training team** experience in industry (highest priority). - Publications at top-tier conferences (**NeurIPS, ICML, ACL**). - Experience training models or evaluating model performance. - Experience with **synthetic data generation**, **LLM evaluations**, or **RL-style workflows**. - Work samples/artifacts/code repositories demonstrating relevant skills. ## Benefits - **$1.5K monthly stipend** for meals - **Free Equinox membership** - **$200 monthly laundry reimbursement** - **$200 monthly personal wellness reimbursement**
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.