Member of Technical Staff - Post Training

Warp • South San Francisco, CA

4d

About The Position

Warp Sciences is building scientific infrastructure in the United States to accelerate the discovery of new medicines by bringing AI, robotics, and life sciences together in increasingly automated laboratories. The company builds infrastructure for research teams rather than maintaining a proprietary drug pipeline.

Warp is seeking a post-training research engineer or scientist to improve the capabilities, reliability, and performance of its AI systems in real use. The AI stack includes local robotics and perception models, cloud foundation models, and the runtime connecting them. The role owns post-training work from identifying capability gaps through evaluation, data development, training, deployment, and production feedback. It requires a track record of meaningful results, rigorous experimentation, strong evaluation practices, deep hands-on reinforcement learning experience, and shipping model improvements into products.

Requirements

• Experience working at the frontier of model capabilities, with meaningful personal ownership of post-training results.
• Demonstrated ability to achieve state-of-the-art results and substantiate them through rigorous evaluation against strong baselines.
• Deep practical experience with reinforcement learning, including reward design, rollout systems, training stability, and diagnosing failure modes.
• An evaluation-led approach: define success before optimizing and scrutinize whether measured gains reflect intended behavior.
• Strong data intuition and experience identifying, creating, and selecting data that produces measurable improvements.
• Strong engineering skills and experience building reliable training and experimentation systems.
• A track record of shipping model improvements into real products and learning from deployment.
• An outcome-driven mindset: follow evidence, move quickly, and take responsibility for whether the work improves the product.

Nice To Haves

• Experience with robotics, embodied AI, or learning from interaction.
• Experience post-training multimodal, perception, or action-generating models.
• Experience balancing model quality with latency, compute, and deployment constraints across local and cloud environments.

Responsibilities

• Own the post-training loop from identifying a capability gap through evaluation, data development, training, deployment, and production feedback.
• Build product-grounded evaluations with clear baselines and held-out tests that distinguish genuine progress from benchmark overfitting.
• Build experimentation systems that support fast, reproducible hill climbing and make results easy to compare and diagnose.
• Develop and improve reinforcement learning methods, reward signals, rollout generation, and supporting infrastructure.
• Curate, generate, and refine training data based on model failures, evaluation results, and product feedback.
• Improve model behavior across Warp’s robotics and foundation-model stack in collaboration with robotics, infrastructure, and product teams.
• Validate gains through ablations, robust comparisons, and testing beyond the training distribution.
• Ship improvements, measure their impact in production, and use the findings to drive subsequent iterations.

What This Job Offers

• Job Type: Full-time
• Education Level: No Education Listed