ML Model Serving Engineer

Sesame HR; San Francisco (CA); On-site; USD 200,000 - 320,000; Full time

Benefits offered by this job

401(k) match

Health, vision, and dental benefits

Unlimited PTO

Flexible spending account (FSA)

EAP

Stock options

Job summary

Sesame is building a next-generation voice-enabled computer and seeks an ML engineering leader to turbocharge our serving layer for LLM, speech, and vision models. You will optimize performance and reliability.

Collaborate with ML infra and training teams to deploy fast, scalable inference, minimize latency, reduce startup times, and implement in-flight batching, caching, and custom kernels. Join a team with deep roots in Oculus, Meta, and beyond.

Qualifications

• Expert in differentiable array computing frameworks, preferably PyTorch.
• Expert in optimizing ML models for serving reliably at high throughput, with low latency.
• Significant systems programming experience; comfortable with internals of VLLM and PyTorch codebases.
• Significant performance engineering experience; bottleneck analysis in high-scale server systems.
• Up-to-date on latest techniques for model serving optimization.

Responsibilities

• Turbocharge our serving layer, consisting of a variety of LLM, speech, and vision models.
• Partner with ML infrastructure and training engineers to build a fast, cost-effective, accurate, and reliable serving layer to power a new consumer product category.
• Modify and extend LLM serving frameworks like VLLM and SGlang to take advantage of the latest techniques in high-performance model serving.
• Work with the training team to identify opportunities to produce faster models without sacrificing quality.
• Use techniques like in-flight batching, caching, and custom kernels to speed up inference.
• Find ways to reduce model initialization times without sacrificing quality.

Skills

PyTorch

High-throughput serving

Low latency optimization

Performance engineering

Systems programming

Tools

VLLM

SGlang

Kubernetes

Job description

About Sesame

Sesame believes in a future where computers are lifelike - with the ability to see, hear, and collaborate with us in ways that feel natural and human. With this vision, we're designing a new kind of computer, focused on making voice agents part of our daily lives. Our team brings together founders from Oculus and Ubiquity6, alongside proven leaders from Meta, Google, and Apple, with deep expertise spanning hardware and software. Join us in shaping a future where computers truly come alive.

Responsibilities:

• Turbocharge our serving layer, consisting of a variety of LLM, speech, and vision models.

• Partner with ML infrastructure and training engineers to build a fast, cost-effective, accurate, and reliable serving layer to power a new consumer product category.

• Modify and extend LLM serving frameworks like VLLM and SGLang to take advantage of the latest techniques in high-performance model serving.

• Work with the training team to identify opportunities to produce faster models without sacrificing quality.

• Use techniques like in-flight batching, caching, and custom kernels to speed up inference.

• Find ways to reduce model initialization times without sacrificing quality.

Required Qualifications:

• Expert in some differentiable array computing framework, preferably PyTorch.

• Expert in optimizing machine learning models for serving reliably at high throughput, with low latency.

• Significant systems programming experience; ex. Experience working on high-performance server systems—you’d be just as comfortable with the internals of VLLM as you would with a complex PyTorch codebase.

• Significant performance engineering experience; ex. Bottleneck analysis in high-scale server systems or profiling low-level systems code.

• Always up to date on the latest techniques for model serving optimization.

Preferred Qualifications:

• Familiarity with high-performance LLM serving; ex. experience with VLLM, SGlang deployment, and internals.

• Experience with a public cloud platform such as GCP, AWS, or Azure.

• Experience deploying and scaling inference workloads in the cloud using Kubernetes, Ray, etc.

• You like to ship and have a track record of leading complex multi-month projects without assistance.

• You’re excited to learn new things and work in a multitude of roles.

Sesame is committed to a workplace where everyone feels valued, respected, and empowered. We welcome all qualified applicants, embracing diversity in race, gender, identity, orientation, ability, and more. We provide reasonable accommodations for applicants with disabilities. Contact [e-mail] for assistance.

Full-time Employee Benefits:

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

• 100% employer-paid health, vision, and dental benefits for you and your dependents

• Unlimited PTO and sick time

• Flexible spending account with employer matching up to $1,650/year (medical FSA)

• Guardian Employee Assistance Program (EAP)

• Opportunity to share in the company's success with competitive stock options

Benefits do not apply to contingent/contract workers.