ML Model Serving Engineer — High-Throughput Inference

Sesame; Bellevue (WA); On-site; USD 175,000 - 280,000; Full time

Benefits offered by this job

401(k) max employer match: 3.5% of compensation

100% employer‑paid health, vision, and dental benefits

Unlimited PTO and sick time

Flexible spending account with employer matching

Guardian Employee Assistance Program (EAP)

Competitive stock options

Job summary

Sesame, located in Bellevue, Washington, is seeking a talented engineer to join our team focused on revolutionizing the way computers interact with humans. The role involves optimizing machine learning models for a new consumer product category, working with state-of-the-art LLM and vision models. Candidates should have significant systems programming and performance engineering experience.

You will enjoy benefits like unlimited PTO, 100% employer-paid health coverage, and competitive stock options. The compensation range for this role is $175K - $280K.

Qualifications

• Expert in some differentiable array computing framework, preferably PyTorch.
• Experience in optimizing machine learning models for high throughput with low latency.
• Extensive experience with complex server systems and performance engineering.

Responsibilities

• Turbocharge our serving layer with various LLM, speech, and vision models.
• Partner with ML engineers to build an efficient and reliable serving layer.
• Modify LLM serving frameworks for high-performance model serving.

Skills

Expert in some differentiable array computing framework

Optimizing machine learning models

Significant systems programming experience

Bottleneck analysis

Staying up to date on model serving optimization

Tools

PyTorch

GCP

AWS

Azure

Kubernetes

Ray

Job description

Sesame, located in Bellevue, Washington, is seeking a talented engineer to join our team focused on revolutionizing the way computers interact with humans. The role involves optimizing machine learning models for a new consumer product category, working with state-of-the-art LLM and vision models. Candidates should have significant systems programming and performance engineering experience.

You will enjoy benefits like unlimited PTO, 100% employer-paid health coverage, and competitive stock options. The compensation range for this role is $175K - $280K.