Staff Engineer, Inference Optimizations

DigitalOcean
San Francisco, California, United States
Full Time
Remote
Senior
USD 191,200 – 239,000
Software Information Technology Telecommunications

Posted 2 days ago

Apply to this job and hundreds more automatically

Get Started
Excellent 4.7

Job summary

The role involves leading performance optimizations for AI inference engines, focusing on GPU kernel tuning, system architecture, and advanced parallelization techniques to maximize throughput and minimize latency for large models. Key responsibilities include hardware-software integration, developing cutting-edge quantization methods, and mentoring teams to achieve high-performance AI inference infrastructure.

Responsibilities

Lead the technical strategy for AI inference optimizations to maximize throughput and minimize latency for large models. Solve complex bottlenecks in memory bandwidth and compute utilization while guiding the technical roadmap for the GPU fleet.

Qualifications

AI infrastructure CUDA GPU Optimization Low-level GPU programming Memory bandwidth optimization Parallelization Performance benchmarking Quantization techniques ROCm TensorRT

Requires 5+ years of experience in high-performance computing or AI infrastructure with expert-level proficiency in Triton or CUDA. Must have deep knowledge of NVIDIA/AMD GPU architectures and experience with LLM optimization techniques.

English

Benefits

  • Employee Assistance Program
  • Local Employee Meetups
  • Flexible Time Off Policy
  • Conference Reimbursement
  • Training And Education Reimbursement
  • LinkedIn Learning Access
  • Bonus
  • Equity Grants
  • Employee Stock Purchase Program

Company

DigitalOcean

DigitalOcean

linkedin
Software Development
Location
San Francisco, California, United States

Apply to this job and hundreds more automatically

Get Started
Excellent 4.7
Pete DeQuarto avatar
Pete DeQuarto

AIApply is a total game-changer. Thanks to Auto-Apply, I have been applying to jobs I would never even have come across otherwise!

Akarshak Tanwar avatar
Akarshak Tanwar

In one week I applied to over 150 jobs and locked in 2 confirmed interviews, with a support team that was quick to respond. The auto-apply feature is fascinating and a real pleasure to use!

JC
Julian Carlin

It really worked. In under 48 hours it had applied to 100 jobs on my behalf without any time or effort from me. I am looking forward to seeing how it keeps improving.