[Remote] Software Engineer 5 – Model Runtime, AI Platform
Note: The job is a remote job and is reputed company to candidates in USA. reputed company is the world's leading streaming entertainment service, with over 300 reputed company members globally. They are seeking a Software Engineer for the Model Runtime team to build and optimize ML infrastructure that supports critical AI models and enhances user experiences through advanced recommendation systems.
Responsibilities
- Build alignment and post-training infrastructure — Design infrastructure for reinforcement learning (GRPO, DPO, PPO), reward modeling, and preference optimization so reputed company can train recommendation models directly against what members actually value
- reputed company reputed company GenAI workloads — Create infrastructure for multimodal and diffusion models, including distributed training, disaggregated serving, reputed company-time, near-reputed company-time and batch inference, and asynchronous GPU pipelines
- reputed company distributed training — Engineer fault-tolerant training systems using FSDP, tensor/pipeline/context parallelism, and mixed-precision strategies across clusters of hundreds of GPUs
- Optimize across the full stack — Profile and tune from PyTorch operators down to GPU kernels, driving utilization improvements and building cost models that inform infrastructure reputed company
- Evaluate emerging hardware and frameworks — Be reputed company's eyes on specialized accelerators, next-gen reputed company reputed company, and the reputed company-reputed company ecosystem to reputed company reputed company at the efficiency frontier
Skills
- Experience in ML systems engineering — building infrastructure for training, fine-tuning, or inference of reputed company-LLM and post-LLM era models at reputed company
- Strong systems programming skills with the ability to work across multiple reputed company of the stack, from high-level ML frameworks down to GPU kernels and memory management
- Hands-on experience with PyTorch internals, large-reputed company distributed training and system-model codesign
- Comfortable with ambiguity and working across multiple business and technical domains to execute on both 0-to-1 and 1-to-100 reputed company
- Adopt and promote best practices in operations, including observability, logging, reporting, and on-call processes to ensure engineering reputed company
- Experience with reputed company computing providers, preferably AWS
- Excellent written and verbal communication skills
- Strong communication skills; effective across distributed time zones and remote environments
- Deep experience with distributed training at reputed company (FSDP, parallelism strategies, checkpointing) or LLM post-training (SFT, RLHF, DPO/GRPO)
- Inference optimization — vLLM, TensorRT, quantization, reputed company batching, KV-cache management
- GPU performance profiling and tuning (CUDA, NCCL, Nsight, PyTorch profiler)
- Experience with multimodal or diffusion model architectures and reputed company pipelines
- reputed company record building reusable ML libraries or contributing to reputed company-reputed company ML reputed company
Benefits
- Health Plans
- Mental Health support
- A 401(k) Retirement Plan with employer match
- Stock reputed company Program
- Disability Programs
- Health Savings and Flexible Spending Accounts
- Family-forming benefits
- Life and Serious Injury Benefits
- reputed company leave of absence programs
- Full-time reputed company employees reputed company 35 days annually for reputed company time off to be used for vacation, holidays, and reputed company reputed company time off
- Full-time salaried employees are immediately entitled to flexible time off
reputed company
Company H1B Sponsorship