技术项目经理，模型性能
Technical Program Manager, Model Performance
ABOUT BASETEN
Baseten 为全球最具活力的 AI 公司提供关键推理支持，如 Cursor、Notion、OpenEvidence、Abridge、Clay、Gamma 和 Writer。通过结合应用 AI 研究、灵活的基础架构和无缝的开发者工具，我们使处于 AI 前沿的公司能够将前沿模型投入生产。我们正在快速成长，并最近完成了 1.5 亿美元的 F 轮融资 https://www.baseten.co/blog/announcing-our-series-f/，由 Altimeter Capital、Conviction Partners 和 Spark Capital 领投。加入我们，帮助构建工程师们用来发布 AI 产品的平台。
THE ROLE
Baseten 的 Model Performance 组织正在寻找我们的第一位技术项目经理。这是一个从零开始的角色，该团队负责构建支撑 Baseten 高性能推理堆栈的核心算法和方法。你不会继承现有的项目框架，而是从零开始构建：规划结构、执行流程、指标以及快速成长组织所需的跨职能对齐。你的贡献将直接影响我们性能研发产品化的速度。如果你能推动一系列雄心勃勃但定义模糊的项目，转化为可预测、良好治理的项目，那么这个角色适合你。
EXAMPLE INITIATIVES
看看我们 Model Performance 团队成员撰写的这些博客文章：
- 如何为 Kimi K3 构建 day-0 API https://www.baseten.co/blog/how-to-build-a-day-zero-api-for-kimi-k3/
- 我们如何构建 GLM-5.2 最快的 API https://www.baseten.co/blog/how-we-built-the-new-fastest-api-for-glm-52/
- DeepSeek V4 Pro 0813 的推理工程 https://www.baseten.co/blog/inference-engineering-for-deepseek-v4-pro-0813/
RESPONSIBILITIES
- 负责 Model Performance 当前项目组合的执行，让技术负责人能够专注于技术方向而非跟踪进度。
- 设计并建立最适合团队基因的规划结构、运营节奏和状态报告机制。
- 全程协调模型发布和优化项目，包括 day-zero 上线，安排性能工程、基础架构和发布相关方的工作顺序。
- 在 Model Performance 核心扩展到 Model APIs 和推理生产堆栈（BIS）时，推动跨团队对齐。
- 提前识别风险和依赖关系，并以清晰、诚实的方式向领导层汇报。
查看英文原文
ABOUT BASETEN
Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F https://www.baseten.co/blog/announcing-our-series-f/, led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to ship AI products.
THE ROLE
The Model Performance organization at Baseten is looking to hire our first Technical Program Manager. This is a zero-to-one role in a team that is responsible for building the core algorithms and methods that power Baseten’s high performance inference stack. You won't inherit an existing program framework, you'll build one from the ground up: the planning structure, execution processes, metrics and the cross-functional alignment that a fast-growing organization needs. Your contributions will directly impact how fast our performance R&D gets productized. If you can drive turning a set of ambitious but loosely defined initiatives into a predictable, well-governed program, this role is for you.
EXAMPLE INITIATIVES
Take a look at these blog posts written by members of our Model Performance team:
- How to build a day-0 API for Kimi K3 https://www.baseten.co/blog/how-to-build-a-day-zero-api-for-kimi-k3/
- How we built the new fastest API for GLM-5.2 https://www.baseten.co/blog/how-we-built-the-new-fastest-api-for-glm-52/
- Inference engineering for DeepSeek V4 Pro 0813 https://www.baseten.co/blog/inference-engineering-for-deepseek-v4-pro-0813/
RESPONSIBILITIES
- Own execution across Model Performance's active project portfolio, freeing the team's technical leads to focus on technical direction rather than tracking.
- Design and stand up the planning structures, operating cadences, and status reporting mechanisms that best fits the team’s DNA.
- Coordinate model release and optimization programs end to end, including day-zero launches, sequencing the work across performance engineering, infra, and release stakeholders.
- Drive cross-team alignment as scope expands from Model Performance Core into Model APIs and the inference production stack (BIS).
- Surface risks and dependencies early, and keep leadership informed with clear, honest status.
- Partner with engineering leads to design team structures and ownership boundaries as the org scales.
REQUIREMENTS
- Deep technical program management experience - you're already running programs of this scope at an organization of similar or greater complexity.
- Experience program-managing model performance or inference optimization work - you understand how engines like vLLM, TensorRT-LLM, SGLang, or NVIDIA Dynamo fit into a production serving stack and can engage credibly with the engineers building on them.
- Demonstrated comfort with ambiguity and zero-to-one program building, not just executing an existing framework.
- Proven ability to influence without authority across engineers, managers, and leadership who don't report to you.
- Excellent written and verbal communication, with the ability to make deeply technical programs legible to any audience.
- High agency decision making that demonstrates ownership, accountability and a strong desire to get things done.
NICE TO HAVE
- Experience coordinating model release programs, including day-zero launches (ideally for large-scale models).
- Prior hands-on software engineering background.
- Deep learning performance optimization background, in training or inference, with inference preferred.
BENEFITS
- Competitive compensation, including meaningful equity
- (U.S. only) 100% coverage of medical, dental, and vision insurance for employee and dependents
- Flexible PTO policy including company wide Winter Break (our offices are closed from Christmas Eve to New Year's Day!)
- Paid parental leave
- Fertility and family-building stipend through Carrot
- Company-facilitated 401(k)
- Exposure to a variety of ML startups, offering unparalleled learning and networking opportunities.
Apply now to embark on a rewarding journey in shaping the future of AI! If you are a motivated individual with a passion for machine learning and a desire to be part of a collaborative and forward-thinking team, we would love to hear from you.
At Baseten, we are committed to fostering a diverse and inclusive workplace. We provide equal employment opportunities to all employees and applicants without regard to race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, or veteran status.
We are an Equal Opportunity Employer and will consider qualified applicants with criminal histories in a manner consistent with applicable law (by example, the requirements of the San Francisco Fair Chance Ordinance, where applicable).