Member of Technical Staff, RL Infra
InceptionVisit Inception website
AI research and product company building diffusion-based language models for production applications.
Palo Alto, United States
Funding history
About Inception
Inception develops and deploys the Mercury family of diffusion LLMs, which generate and refine output in parallel to target lower-latency, lower-cost production AI workloads.
Skills
About the Role
You will design and optimize infrastructure for large-scale reinforcement learning and post-training workloads. You will improve distributed pipeline reliability and throughput and create monitoring and observability tools for stable, debuggable, reproducible RL systems.
Requirements
- PyTorch
- TensorFlow
- Ray
- Megatron
- Reinforcement learning
- PPO
- DPO
- RLHF
- Reward modeling
- Docker
- Kubernetes
- CI/CD
Responsibilities
- Build infrastructure for large-scale reinforcement learning and post-training workloads
- Improve reliability and scalability of distributed reinforcement learning pipelines
- Improve training throughput for reinforcement learning workloads
- Develop monitoring and observability tools for reinforcement learning systems
Benefits
- Equity
- Flexible vacation and paid time off
- Health insurance
- Dental insurance
- Vision insurance
- 401k match
- Catered meals
- Commuter subsidies