Embedding VC
Member of Technical Staff — RL & Agentic Model Training
San Francisco Bay Area · On-site · Staff · Full-time · Posted Oct 22, 2026
About the job
Lead reinforcement-learning infrastructure and agent post-training to improve multimodal, vision-language, and code-generating agents for interactive environments.
What you'll do
- Build RL, supervised fine-tuning, preference-optimization, and reward-modeling pipelines.
- Develop systems for collecting and learning from agent trajectories, and design rewards, verifiers, and evaluations.
- 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 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
Develop and scale post-training and reinforcement-learning systems for vision-language, multimodal, code-generating, and embodied agents, including trajectory learning, reward design, and evaluation.
Model-written summary · the original posting is authoritative