--- title: 'ML Model Serving Engineer at Sesame' canonical: 'https://feeny.ai/job/ml-model-serving-engineer-sesame-san-francisco-mhgmywb7k1b2' type: 'job' last_seen: '2026-11-07' --- # ML Model Serving Engineer at Sesame - **Company:** Sesame - **Location:** San Francisco, CA - **Compensation:** $175k–$280k - **Employment:** full-time - **Work type:** onsite - **Posted:** 2026-11-03 - **Last confirmed live:** 2026-11-07 - **Apply:** https://jobs.ashbyhq.com/sesame/35793528-2b5c-47b3-9422-eaced2b69f63/application **Skills:** PyTorch, Differentiable Array Computing, Systems Programming, Performance Engineering, Bottleneck Analysis, Profiling, VLLM, SGLang, GCP, AWS, Azure, Kubernetes, Ray, Cloud Deployment > The ML Model Serving Engineer will optimize and scale the serving layer for LLM, speech, and vision models. Responsibilities include modifying serving frameworks like VLLM and SGLang, implementing performance techniques such as batching and caching, and collaborating with infrastructure teams to ensure high-throughp... ## 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 careers@sesame.com 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. ## About Sesame ## Company Overview - **One-liner**: Sesame is building lifelike, conversational AI agents integrated into lightweight eyewear, aiming to bring ambient intelligence to daily life. - **Entity Type**: Private (early-stage, backed by prominent venture firms) - **Headquarters**: San Francisco, California, USA - **Founded**: 2023 - **Founders**: Brendan Iribe, Ankit Kumar, Ryan Brown, Angela Gayles, Nate Mitchell ## Core Business - **Primary industry**: Artificial intelligence / Voice assistants / Consumer electronics - **Target customers**: Consumer (B2C) – individuals seeking hands-free, intelligent personal agents integrated into everyday eyewear - **Mission or purpose statement**: “Bringing the computer to life” – creating a personal companion that understands you, with natural conversation and lightweight, all-day wearable hardware. ## Products & Services - **Sesame Personal Agents**: Software-based conversational AI agents capable of natural dialogue, personality modeling, and multimodal interaction (voice, gesture). Currently in development; initial hardware (eyewear) targeted for 2027. - **Sesame Eyewear**: Lightweight, all-day comfortable glasses with high-quality audio and hands-free agent access. Coming 2027. - **Research Platform**: In-house deep learning research covering speech generation, personality modeling, multimodality, and scaled training infrastructure. ## Market Standing - **Valuation/Market Cap**: Not publicly available. Unconfirmed reports suggest a potential fundraising round of ~$200 M (source: Techmeme via LinkedIn snippet). The company has not officially disclosed its valuation. - **Key Metric**: Total employees ~70 (as of mid-2026), with +5.8 % monthly headcount growth. - **Notable Investors/Partners**: Backed by a16z, Sequoia Capital, Spark Capital, Matrix Partners, plus a collection of founders and investors. - **Growth Signals**: 55 total employees on BuiltIn (likely older data); 63 active job postings (+14.5 % monthly trend); monthly LinkedIn follower growth of +3.8 % (20,969 followers). Talent sources include Meta, Apple, Google, DeepMind, and Microsoft. ## Competitive Advantages - **Interdisciplinary approach**: Tightly integrated hardware, software, and ML teams (hardware engineers, ML researchers, product designers) working on a unified product vision. - **Founding team pedigree**: Led by Oculus VR veterans (Brendan Iribe, Nate Mitchell) and experienced AI/ML innovators, giving deep expertise in both consumer hardware and conversational AI. - **Research depth**: Active push in speech generation, personality modeling, and multimodality, with scaled GPU infrastructure for training. ## Strategic Focus - **Near-term**: Ship the first generation of personal agent software and finalize the eyewear device for a 2027 launch. Continue advancing foundational ML research. - **Long-term**: Build a new category of ambient, always-available AI companions that replace traditional screen-based interaction. - **Growth areas**: Expanding engineering team rapidly (63 open roles), especially in ML, embedded systems, iOS/Android, supply chain, and hardware. ## Why Work Here - **Culture**: Small, focused, interdisciplinary team with a clear vision. Emphasis on tight collaboration between research, product, and hardware. Described as “artists, makers, and engineers.” - **Work environment**: In-office for most roles (San Francisco, Bellevue, New York). Roles are listed as “In-Office” (not remote/hybrid). Offices in SF, Bellevue, NY. - **Perks & engineering culture**: Not explicitly detailed, but the company invests heavily in infrastructure (GPU clusters) and research. Strong engineering focus with roles spanning embedded ML, OS architecture, and developer infrastructure. - **Notable**: Opportunities to work on cutting-edge voice AI and physical product design from the ground up. ## Sources 1. [sesame.com](https://www.sesame.com/) – Company overview and product vision 2. [sesame.com/team](https://www.sesame.com/team) – Leadership, investors, team description 3. [builtin.com](https://builtin.com/company/sesame-sesamecom) – Founded year, HQ, employee count, office policy 4. [linkedin.com](https://www.linkedin.com/company/sesameai) – Employee count, growth, talent sources, funding rumor 5. [jobs.ashbyhq.com](https://jobs.ashbyhq.com/sesame) – Open positions and location details ## Other roles at Sesame - [Audio Systems Engineer](https://feeny.ai/job/audio-systems-engineer-sesame-san-francisco-9s82kaxpfwej) — San Francisco, CA - [Technical Program Manager, Product Design](https://feeny.ai/job/technical-program-manager-product-design-sesame-san-francisco-c39j4ewzmywn) — San Francisco, CA - [Fabrication Shop Manager](https://feeny.ai/job/fabrication-shop-manager-sesame-bellevue-z681vhqvvavf) — Bellevue, WA - [Product Engineering Lead](https://feeny.ai/job/product-engineering-lead-sesame-san-francisco-frrrpwp06s6z) — San Francisco, CA - [Executive Assistant](https://feeny.ai/job/executive-assistant-sesame-new-york-e0mdmkv43s9f) — New York, NY - [Research Scientist](https://feeny.ai/job/research-scientist-sesame-san-francisco-dn2g1qez13fh) — San Francisco, CA - [Hardware Test Automation Engineer](https://feeny.ai/job/hardware-test-automation-engineer-sesame-san-francisco-fvyd7w3bj32c) — San Francisco, CA - [NPI Engineer](https://feeny.ai/job/npi-engineer-sesame-taipei-ezvdh72dn9yg) — Taipei, Taiwan - [Manufacturing Mechanical Engineer](https://feeny.ai/job/manufacturing-mechanical-engineer-sesame-san-francisco-w823rcvz6t4s) — San Francisco, CA - [Executive Assistant](https://feeny.ai/job/executive-assistant-sesame-san-francisco-h3w69r7cbk2s) — San Francisco, CA