Member of Engineering (Reinforcement Learning Infrastructure)

📋 Description

• Keep up with latest research in LLMs, RL, and code generation
• Develop end-to-end training and inference tuning for throughput
• Design data control systems in an RL pipeline
• Debug cases where infrastructure decisions degrade learning dynamics
• Build observability tooling for root-cause training regressions
• Help build robust, scalable RL pipelines
• Optimize performance across the stack — networking, memory, compute scheduling, and I/O
• Write high-quality, pragmatic code
• Work in the team: plan future steps, discuss, and stay in touch

🎯 Requirements

• Experience with LLMs and post-training workflows
• Understanding RL bottlenecks
• Python with concurrency, async, multiprocessing, and optimization
• PyTorch and/or JAX with RL workflows (rollouts, replay buffers, policy updates)
• Designing and maintaining distributed RL training systems
• Experience with large-scale LLM training infrastructure
• Experience with profiling tools (e.g., py-spy)
• Open-source contributions to RL or distributed ML projects (nice to have)

🎁 Benefits

• Fully remote work and flexible hours
• 37 days of vacation and holidays
• Health insurance allowance for you and dependents
• 16 weeks of flexible, full-pay parental leave
• Well-being, learning and home office allowances
• Company-provided equipment
• Frequent team get-togethers
• Diverse and inclusive people-first culture