Baseten

2 weeks ago

Engineering Manager

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 23 minutes agoStatus: Live

Job Summary

Lead and grow a GPU Kernel Engineering team in a player-coach role, owning the technical direction and roadmap for CUDA kernels that power Baseten’s inference stack. Partner with the Chief Scientist, VP Engineering, and other engineering leaders to align kernel work across GPU architecture, ML systems, and production inference. Maintain a high quality and performance bar using profiling tools, unblock execution, and represent the team through conferences and open-source contributions.

Location: San Francisco, New York

Workplace: Hybrid

Employment Type: Full time

Job Function: Software Engineering

Seniority: Manager level

Key Responsibilities

•Lead, grow, and mentor a team of GPU kernel engineers, including hiring, performance, and career development.
•Set technical direction for the kernel roadmap, balancing short-term inference wins with long-term architectural investments.
•Partner with the Chief Scientist, VP Engineering, and peer engineering leads to align kernel work with the broader inference stack strategy.
•Drive cross-functional collaboration between kernel engineering and Model Performance, Capacity, and Infrastructure teams.
•Establish and maintain a high technical bar for kernel quality, performance, and correctness; guide profiling and bottleneck identification using Nsight Systems, Nsight Compute, and Torch Profiler.

Pay and Benefits

Salary: USD 260,000 - 380,000 annually

Equity and Bonus:Equity

Perks:Health InsuranceDentalVisionParental Leave401k

Key Requirements

•Proven experience leading a team of GPU or ML systems engineers, including hiring and developing technical talent.
•Deep hands-on background in GPU kernel engineering; have written and shipped production CUDA kernels.
•Strong GPU architecture fundamentals, including memory hierarchy, warp execution, tensor cores, occupancy tradeoffs, and profiling methodology.
•Experience with NVIDIA GPU architectures (Hopper or Blackwell preferred) and the CUDA ecosystem.
•Ability to set technical direction, prioritize a roadmap, and communicate clearly across engineering and leadership.

Experience:GPU kernel engineeringML systemsLLM inference

Skills:LeadershipMentorshipTechnical communicationRoadmap planningProcess building

Tech Stack:CUDAGPU architectureNVIDIA HopperNVIDIA BlackwellNsight SystemsNsight ComputeTorch ProfilerTritonCUTLASSCuTe DSLGEMMsMoE routingTensor coresWarpsProfilingFP8FP4

Company Brief

Baseten

Baseten provides an inference-first ML infrastructure platform that lets engineering and ML teams deploy, serve, and scale machine-learning models with optimized performance, autoscaling, and GPU-backed hosting for production AI applications. ([crunchbase.com](https://www.crunchbase.com/organization/baseten?utm_source=openai))

Industry: AI & Machine Learning

Company Size: Medium (51 to 250 employees)

Growth: Scaleup

Valuation: Unicorn (USD 1B+)

Funding: Series E+

Headquarters: San Francisco, United States

Founded: 2019

Glassdoor: 5.0

Website LinkedIn Glassdoor

Loading job details...

Preparing the role view and application actions.

Baseten

2 weeks ago

Engineering Manager

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 23 minutes agoStatus: Live

Job Summary

Location: San Francisco, New York

Workplace: Hybrid

Employment Type: Full time

Job Function: Software Engineering

Seniority: Manager level

Key Responsibilities

•Lead, grow, and mentor a team of GPU kernel engineers, including hiring, performance, and career development.
•Set technical direction for the kernel roadmap, balancing short-term inference wins with long-term architectural investments.
•Partner with the Chief Scientist, VP Engineering, and peer engineering leads to align kernel work with the broader inference stack strategy.
•Drive cross-functional collaboration between kernel engineering and Model Performance, Capacity, and Infrastructure teams.
•Establish and maintain a high technical bar for kernel quality, performance, and correctness; guide profiling and bottleneck identification using Nsight Systems, Nsight Compute, and Torch Profiler.

Pay and Benefits

Salary: USD 260,000 - 380,000 annually

Equity and Bonus:Equity

Perks:Health InsuranceDentalVisionParental Leave401k

Key Requirements

•Proven experience leading a team of GPU or ML systems engineers, including hiring and developing technical talent.
•Deep hands-on background in GPU kernel engineering; have written and shipped production CUDA kernels.
•Strong GPU architecture fundamentals, including memory hierarchy, warp execution, tensor cores, occupancy tradeoffs, and profiling methodology.
•Experience with NVIDIA GPU architectures (Hopper or Blackwell preferred) and the CUDA ecosystem.
•Ability to set technical direction, prioritize a roadmap, and communicate clearly across engineering and leadership.

Experience:GPU kernel engineeringML systemsLLM inference

Skills:LeadershipMentorshipTechnical communicationRoadmap planningProcess building

Tech Stack:CUDAGPU architectureNVIDIA HopperNVIDIA BlackwellNsight SystemsNsight ComputeTorch ProfilerTritonCUTLASSCuTe DSLGEMMsMoE routingTensor coresWarpsProfilingFP8FP4

Company Brief

Baseten

Industry: AI & Machine Learning

Company Size: Medium (51 to 250 employees)

Growth: Scaleup

Valuation: Unicorn (USD 1B+)

Funding: Series E+

Headquarters: San Francisco, United States

Founded: 2019

Glassdoor: 5.0

Website LinkedIn Glassdoor