RL Infrastructure Engineer — Scale & Production

Inception; San Francisco (CA); On-site; USD 200,000 - 350,000; Full time

Benefits offered by this job

Health, dental, and vision insurance

Catered meals (breakfast, lunch, &

Equity

Flexible vacation and PTO

Job summary

Inception is seeking engineers and scientists to design, optimize, and maintain core systems enabling scalable, efficient reinforcement learning for large models.

This role sits at the intersection of research and large-scale systems engineering, with duties ranging from optimizing rollout and reward pipelines to improving reliability, observability, and orchestration in close collaboration with researchers.

Qualifications

• BS/MS/PhD in Computer Science, Engineering, or a related field (or equivalent experience).
• Understanding of ML frameworks from a systems perspective (PyTorch, TensorFlow, Ray, Megatron).
• Experience with reinforcement learning workloads (PPO, DPO, RLHF, or reward modeling).
• Experience with containerization (Docker), orchestration (Kubernetes), and CI/CD pipelines.

Responsibilities

• Design, build, and optimize the infrastructure that powers large-scale reinforcement learning and post-training workloads.
• Improve the reliability and scalability of RL training pipelines, distributed RL workloads, and training throughput.
• Develop shared monitoring and observability tools to ensure high uptime, debuggability, and reproducibility for RL systems.

Skills

ML systems understanding

Reinforcement learning workloads

Distributed systems

Experience with RL pipelines

CI/CD

PyTorch/TensorFlow

Ray/Megatron

Education

BS/MS/PhD in CS or Engineering (or equivalent)

Tools

Docker

Kubernetes

CI/CD tooling

Ray

Megatron

PyTorch

TensorFlow

Job description

Inception is seeking engineers and scientists to design, optimize, and maintain core systems enabling scalable, efficient reinforcement learning for large models.

This role sits at the intersection of research and large-scale systems engineering, with duties ranging from optimizing rollout and reward pipelines to improving reliability, observability, and orchestration in close collaboration with researchers.