Warp Sciences
Member of Technical Staff - Post Training
South San Francisco · On-site · Staff · Full-time · Posted Oct 21, 2026
About the job
Own the post-training cycle for Warp’s AI systems, improving model capabilities, reliability, and product performance through evaluation, data development, reinforcement learning, deployment, and production feedback.
What you'll do
- Lead post-training from identifying capability gaps through evaluation, data development, training, deployment, and production feedback.
- Build rigorous evaluations and reproducible experimentation systems; develop reinforcement-learning methods, reward signals, and rollout infrastructure.
- Improve models, validate results, ship gains into products, and use production feedback to guide further iterations.
What they ask for
- Frontier model-capability experience with meaningful personal ownership of post-training results.
- Demonstrated state-of-the-art results supported by rigorous evaluation against strong baselines.
- Deep practical reinforcement-learning experience, including reward design, rollout systems, training stability, and failure diagnosis.
- Strong engineering and data skills, including building reliable training and experimentation systems and shipping model improvements into products.
Nice to have
- Experience with robotics, embodied AI, or learning from interaction.
- Experience post-training multimodal, perception, or action-generating models, or balancing model quality with deployment constraints.
AI focus
Post-training AI systems across robotics and foundation models, including reinforcement learning, model evaluation, training data development, and deployment into products.
Model-written summary · the original posting is authoritative