Senior Software Engineer, RL Post-Training Frameworks

This is a fully remote position, open to applicants in Germany.

📋 Description

• Design and construct RL post-training infrastructure that efficiently scales from experimentation on a single GPU to deployment across thousands of nodes.

• Optimize RL training-inference-rollout loops on GPUs, CPUs, and LPUs for critical performance enhancements.

• Contribute to and enhance the performance and usability of open-source RL frameworks.

• Collaborate with teams developing CPU-driven rollout workloads, encompassing tool usage, code execution, and agentic environments.

• Represent the needs of researchers and partners with NVIDIA's networking, math library, and compiler teams.

⛳️ Requirements

• MS or PhD in Computer Science, Computer Engineering, or a related discipline (or equivalent experience).

• Over 5 years of professional experience in distributed systems, high-performance computing, deep learning infrastructure, or ML systems engineering.

• Strong expertise in Python and C/C++.

• Proven experience in building or contributing to large-scale distributed systems or runtime frameworks in production at a leading AI lab, hyperscaler, or major tech company.

• Excellent verbal and written communication skills with the ability to collaborate across organizational and geographic boundaries.

• In-depth knowledge in one or more of the following technical areas: Reinforcement learning for LLM post-training (RLHF, PPO, GRPO, DPO, reward modeling), including the mapping of algorithms to distributed execution and the related system challenges (heterogeneous placement, rollouts, environment execution, resharding between training and generation).

• Familiarity with PyTorch internals, including distributed training primitives (FSDP, tensor parallelism, pipeline parallelism) and their integration.

• Understanding of Kubernetes runtime internals (container lifecycle, pod scheduling, resource quotas, GPU allocation).

• Comprehensive knowledge of end-to-end distributed systems design (service boundaries, data flows, consistency models, failure modes, recovery strategies).

🏝️ Benefits

• Highly competitive salaries.

• Comprehensive benefits package.