ML Model Serving Engineer (AI)

TL;DR

ML Model Serving Engineer (AI): Turbocharging the serving layer for LLM, speech, and vision models with an accent on optimizing high-performance model serving techniques. Focus on modifying frameworks, reducing initialization times, and collaborating with ML infrastructure teams.

Location: San Francisco, New York, Bellevue

Compensation Range: $175K - $280K

Company

Sesame is focused on creating lifelike computers that can see, hear, and collaborate with humans.

What you will do

• Turbocharge the serving layer for various models.
• Collaborate with ML infrastructure and training engineers.
• Modify and extend LLM serving frameworks.
• Identify opportunities for faster model production.
• Implement techniques to speed up inference.
• Reduce model initialization times.

Requirements

• Expert in PyTorch or similar frameworks.
• Experience in optimizing ML models for high throughput.
• Significant systems programming experience.
• Performance engineering experience in high-scale systems.
• Up-to-date with model serving optimization techniques.

Nice to have

• Familiarity with high-performance LLM serving.
• Experience with cloud platforms like GCP, AWS, or Azure.
• Experience deploying workloads using Kubernetes.
• Track record of leading complex projects.
• Willingness to learn and adapt.

Culture & Benefits

• 401k matching.
• 100% employer-paid health, vision, and dental benefits.
• Unlimited PTO and sick time.
• Flexible spending account matching.