Research, Post-Training Data

📋 Description

• Data Strategy: Design data collection and synthesis to guide model behavior.
• Scalable Pipelines: Build labeling pipelines and synthetic data generation.
• Human Preference Modeling: Model human preferences to improve reasoning.
• Evaluation Design: Define evaluations and identify gaps.
• Metrics & Benchmarks: Create metrics for data quality and impact.
• Scaling & Exploration: Scale methodologies and push new ideas.

🎯 Requirements

• Strong engineering skills with ability to debug in complex codebases.
• Experience with data curation, human feedback, or synthetic data for large language models.
• Design, run, and interpret experiments with scientific rigor.
• Python and at least one DL framework (PyTorch, TensorFlow, or JAX).
• Understand probability, statistics, and ML fundamentals.
• Experience with RLHF, RLAIF, or reward learning for large models.

🎁 Benefits

• Small, selective team where research and product move together.
• Access to data, tooling, and compute for frontier-scale experiments.
• Environment rewards speed, autonomy, and technical depth in AI.