Embedding VC
Member of Technical Staff — Post-Training Infrastructure
San Francisco Bay Area · On-site · Staff · Full-time · Posted Oct 22, 2026
About the job
Leads reinforcement-learning infrastructure and model post-training to improve multimodal agents and prepare them for robotics and embodied-AI tasks.
What you'll do
- Build RL and post-training pipelines, including systems for fine-tuning, preference optimization, reward modeling, and reinforcement learning.
- Develop trajectory-data, reward, verification, and evaluation systems for long-horizon agent tasks.
- Scale distributed training and rollout generation while improving reliability, reproducibility, observability, and cost efficiency.
What they ask for
- Real-world experience training large language, vision-language, multimodal, or code models.
- Strong experience in reinforcement learning, post-training, or large-scale fine-tuning.
- Experience building distributed training or high-throughput inference systems.
- Strong Python skills and experience with PyTorch, JAX, or similar frameworks.
Nice to have
- Experience at a frontier AI lab or an organization operating large-scale training systems.
- Experience with code-model post-training, autonomous coding agents, multimodal models, robotics, simulation, or embodied AI.
Tools
Python, PyTorch, JAX
AI focus
Post-trains multimodal, vision-language, and code-generating agents using fine-tuning, reinforcement learning, trajectory data, and scalable evaluation for agent, robotics, and embodied-model tasks.
Model-written summary · the original posting is authoritative