Member of Technical Staff, Post-Training, RL
Mirendil · San Francisco
Frontier labonsite$300k–$400k
At a glance
Highlights
- Design and run experiments turning strong base models into reliable reasoners.
- Scale RL to longer trajectories, larger models, and bigger compute budgets.
- Build robust verifiers and debug reward signals across multi-task training.
What they offer
- Meaningful equity grant
- Competitive benefits
Ideal candidate
A research-minded engineer fascinated by training dynamics who loves forming hypotheses, running large experiments, and digging into traces to turn frontier base models into reliable problem-solvers.
Requirements
- Strong engineering skills
Lab profile
About Mirendil
Frontier AI research company training its own models to accelerate science and technology.
Known for
- End-to-end frontier model training
- Pretraining and custom ML kernels
- RL post-training and environments
- Evaluation, inference and recursive self-improvement
Posted · Last seen