ML Engineer, Inference & Optimization
… · Remote · US remote ·
COMPENSATION
Salary available to subscribersListed on the employer's job board (Ashby)
- Senior/Staff level
- CUDA + NCCL
- Video gen models
- Equity offered
Join the company as an Inference Engineer to enhance the speed and efficiency of their AI-driven video generation products. You will design optimized inference pipelines and implement advanced acceleration techniques to support real-time user experiences at scale.
Working closely with research and engineering teams, you will push the boundaries of model deployment. Your work will directly impact the performance of next-generation video and large language models.
What you'll do
- Lead implementation of inference acceleration techniques like quantization
- Optimize GPU strategies using tensor, sequence, and pipeline parallelism
- Develop high-performance computing kernels and distributed workloads
Loading…