Technical Program Manager, Model Performance
Build and lead the Model Performance organization’s technical program framework, coordinating model releases, inference optimization, and cross-functional execution. The role requires deep technical program management experience and credibility with model-serving and performance engineering teams.
About the job
Responsibilities
- Own execution across the Model Performance project portfolio, allowing technical leads to focus on technical direction.
- Design and establish planning structures, operating cadences, and status-reporting mechanisms.
- Coordinate model release and optimization programs end to end, including day-zero launches and sequencing work across performance engineering, infrastructure, and release stakeholders.
- Drive cross-team alignment as scope expands from Model Performance Core into Model APIs and the inference production stack.
- Surface risks and dependencies early and keep leadership informed with clear, accurate status.
- Partner with engineering leads to design team structures and ownership boundaries as the organization scales.
Requirements
- Deep technical program management experience running programs of comparable scope and complexity.
- Experience program-managing model performance or inference optimization work.
- Working knowledge of production serving engines and frameworks such as vLLM, TensorRT-LLM, SGLang, or NVIDIA Dynamo.
- Experience building zero-to-one program structures in ambiguous environments.
- Ability to influence engineers, managers, and leadership without direct authority.
- Excellent written and verbal communication skills, including the ability to explain highly technical programs to varied audiences.
- High-agency decision-making, ownership, accountability, and execution.
Nice to have
- Experience coordinating model release programs, including day-zero launches for large-scale models.
- Prior hands-on software engineering experience.
- Deep learning performance optimization experience in training or inference, preferably inference.
Compensation and benefits
- Salary range: $165,000-$330,000, plus meaningful equity.
- Medical, dental, and vision insurance fully covered for employees and dependents.
- Flexible paid time off, including a company-wide winter break.
- Paid parental leave.
- Fertility and family-building stipend.
- Company-facilitated 401(k).
Skills
Technical Program Management, Model Performance, Inference Optimization, vLLM, Tensorrt-Llm, Sglang, Nvidia Dynamo, Model Releases, Deep Learning, Software Engineering, Production Serving
Similar jobs
Technical Program Management jobs
Scale AI
Washington, DC
Manages subcontractor relationships and execution for complex Public Sector programs, integrating external deliverables into technical plans and schedules. The role requires 5+ years of program or subcontract management experience, strong systems integration fluency, and an active Top Secret clearance.
Scale AI
Colorado Springs, COOwn technical execution for national security programs, translating operational needs into executable requirements and coordinating engineering, customer, and partner stakeholders through deployment and evaluation. The role requires 5+ years of technical delivery experience, strong software and AI/ML literacy, and an active TS/SCI clearance.
Figma
San Francisco, CALeads cross-functional information security programs, risk remediation, metrics, governance, and organizational engagement while partnering with security leadership and business stakeholders. Requires 5+ years of security program management experience and familiarity with major security frameworks and risk practices.
Lightning AI
New York, NYLeads infrastructure delivery workstreams spanning compute, networking, storage, hardware, platform engineering, and data center operations. Requires 5+ years of technical program management experience, strong cross-functional execution, and familiarity with infrastructure environments.
Decagon
New York, NY
Own complex enterprise deployments and internal cross-functional programs, translating evolving customer requirements into executable plans and coordinating dependencies across technical and business teams. The role requires 4–6+ years of program or product/engineering operations experience, strong technical fluency, and the ability to lead without authority.