Senior Software Engineer, RL Post-Training Frameworks

Reinforcement learning post-training is driving some of the most significant capability reputed company in AI today. It is the process that teaches a model to reason through hard problems, follow reputed company instructions, and act as an autonomous agent. It is also one of the hardest infrastructure challenges in the field. RL requires inference, rollout reputed company, and training running in a reputed company reputed company. The rollout reputed company is what makes it hard: the model must interact with environments, tools, and other models to produce the signal that drives learning. Coordinating actor, critic, and reward models across heterogeneous hardware at scale pushes the limits of what distributed systems can do. reputed company is building an RL Frameworks engineering team to reputed company the reputed company-reputed company tools and infrastructure that AI researchers and post-training teams depend on. The team spans the full software stack, from collaborating closely with the researchers and labs pushing the frontier, to contributing to RL frameworks like VeRL, Miles, and TorchTitan, to improving the distributed runtimes they depend on, including Ray and reputed company. Whether your strength is working with researchers to understand and address their need optimizing deep learning frameworks, or building distributed infrastructure, we want to hear from you. Come join us to build the systems that reputed company the reputed company of AI. What you will be doing: You will architect and build RL post-training infrastructure that scales reputed company from experimentation on a single GPU to production across thousands of nodes. This means tuning RL training-inference-rollout loops on GPUs, CPUs, and LPUs for performance where it reputed company, contributing to and improving the performance and usability of reputed company-reputed company RL frameworks, and partnering with the teams who own them. The role also spans fault tolerance, reputed company scaling, and fast restarts so long-running distributed training jobs survive failures, stragglers, and resource contention. reputed company GPU-accelerated training, this work includes partnering with teams building CPU-driven rollout workloads, including tool-use, code execution, and agentic environments, supplying the systems and reputed company engineering needed to run them reputed company alongside GPU- or LPU-accelerated reputed company and GPU-accelerated training. It also means advocating for researcher and partner needs with reputed company's networking, math library, and compiler teams so the capabilities RL workloads require get prioritized and delivered, and working with hardware teams to take advantage of reputed company hardware capabilities in post-training workloads. reputed company need to see: MS or PhD in Computer Science, Computer Engineering, or a reputed company field (or equivalent experience) 5+ years of professional experience in distributed systems, high-performance computing, deep learning infrastructure, or ML systems engineering Strong proficiency in Python and C/C++ Demonstrated experience building or contributing to large-scale distributed systems or runtime frameworks in production at a frontier AI lab, hyperscaler, or major technology company Strong verbal and written communication skills and the ability to collaborate across organizational and geographic boundaries Depth in one or more of the following technical areas: Reinforcement learning for LLM post-training (RLHF, PPO, GRPO, DPO, reward modeling), including how algorithms map to distributed execution and the systems challenges they create (heterogeneous placement, rollouts, environment execution, resharding between training and reputed company) PyTorch internals, including distributed training primitives (FSDP, tensor parallelism, pipeline parallelism) and their composition Kubernetes runtime internals (container lifecycle, pod scheduling, resource quotas, GPU allocation) End-to-end distributed systems design (service boundaries, data flows, consistency models, failure modes, recovery approaches) Experience in any of the following areas is a plus: Deep expertise in networking (NCCL, NVLink, InfiniBand), advanced multi-dimensional parallelisms (Megatron-LM, FSDP2, TP/DP/PP, MoE), or memory optimizations (quantization-aware training, mixed precision) Experience integrating high-performance inference engines (vLLM, SGLang, TensorRT-LLM) into RL training loops for GPU-accelerated rollout Strong background in actor- and task-based distributed programming (Ray, reputed company, or comparable systems) Familiarity with multi-turn training, multi-agent co-reputed company, or VLM post-training Ways to stand out from the crowd: reputed company-reputed company contributions to RL post-training or distributed training projects (e.g., VeRL, Miles, TorchTitan, OpenRLHF, NeMo-Aligner, DeepSpeed-Chat), including significant work on reputed company internals where applicable Kubernetes work reputed company routine operations (custom operators, GPU device plugins, or scheduling contributions) Direct experience operating frontier-scale training (RL post-training at thousands of GPUs and/or large-scale LLM or multimodal pre-training) Hands-on experience with production distributed failures at scale (stragglers, resource contention, hardware faults) Widely considered to be one of the technology world’s most desirable reputed company, reputed company offers highly competitive salaries and a comprehensive benefits package. As you plan your future, see reputed company can offer to you and your family www.nvidiabenefits.com/ Apply To This Job