Cognition01.05.2026
Research, Post-Training
Полная занятостьОфис
Обязанности
- 01Post-Training Recipe Development: Iterate on the full stack of datasets, training stages, and hyperparameters that determine model behavior
- 02Evaluation Design and Integrity: Build evals that actually capture what matters
- 03Deep Understanding: When training produces results that don't make sense, you dig until you understand why
- 04Alignment and Agent Behavior: Apply and advance techniques like RLHF, RLAIF, and constitutional approaches to shape how agents reason, act, and collaborate with humans in long-horizon tasks
- 05Scaling and Exploration: Measure how performance scales with data and compute, and develop new methodologies when existing ones hit ceilings
Требования
- 01A track record of advancing ML systems through post-training, alignment, or related methods: RLHF, RLAIF, preference modeling, reward learning, or equivalent
- 02Strong fundamentals in probability, statistics, and ML theory. The ability to look at experimental data and distinguish real effects from noise and bugs
- 03Evidence of original contributions: publications at top venues, open-source impact, or equivalent industry results
- 04Experience with large-scale distributed training and the debugging that comes with it
- 05Systems-level thinking: not just model optimization, but understanding how training pipelines, data, and evaluation interact
- 06Comfort with ambiguity and fast-moving research environments where priorities shift quickly
Условия
- 01Small, highly selective team where research and product move together; prototypes reach real deployment quickly
- 02Compute is not a constraint: large allocations with training jobs routinely running across thousands of GPUs from day one
- 03The environment rewards speed, autonomy, and technical depth with minimal process overhead; this is one of the most competitive and fast-moving problems in AI
- 04Everything needed to operate at frontier scale from day one