Where you can live
Open to people living in United States.
Listed location: US remote
Taken from the location the company listed. Confirm in the posting before you apply.
What the job is
Speeds up Pika's video and language model serving by optimizing inference pipelines, GPU parallelism, and CUDA/NCCL kernels, and mentors engineers.
What they ask for
- 5+ years engineering experience with inference acceleration and model deployment at scale
- Proven inference optimization skills: quantization, attention acceleration, deep learning compiler stacks
- Deep knowledge of GPU programming (CUDA, NCCL)
- Experience with SP, TP, PP and other parallelism for distributed inference
- Familiarity with video generation and large language models
Nice to have
- Experience with high-throughput video or real-time streaming model deployment
- Familiarity with distributed training and optimization toolkits
- Open source contributions in AI infrastructure or deep learning compilers
This is a summary written by software from the company's posting. The posting is the source.
More remote jobs at Pika