GPU Kernel Engineer at Baseten

San Francisco, California, United States

Apply Now

$185,000 – $250,000Compensation

Senior (5 to 8 years)Experience Level

Full TimeJob Type

UnknownVisa

AI, Machine LearningIndustries

Requirements

1–5 years of experience in CUDA development
Strong understanding of GPU architecture and programming paradigms: Memory hierarchy (global, shared, registers, L1/L2 cache), Thread/block/grid organization, Synchronization techniques and race condition mitigation
Proficient in C++ and GPU performance profiling tools
Knowledge of: CUDA C++ API, Memory access patterns and bandwidth optimization, Numerical precision and quantization strategies, Modern GPU features (e.g., tensor cores, async operations)

Responsibilities

Design and implement high-performance GPU kernels for key ML operations, including matrix multiplications, attention mechanisms, and mixture-of-experts routing
Write and optimize code using CUDA, PTX assembly, and architecture-specific techniques
Apply advanced performance optimization methods such as memory coalescing, warp-level programming, tensor core acceleration, and compute/memory overlap
Implement cutting-edge features like quantization (FP8/FP4), sparsity, and compute/communication overlap
Identify and resolve performance bottlenecks using tools like Nsight Systems, Nsight Compute, and Torch Profiler
Collaborate with research teams to productionize theoretical advancements
Contribute to internal and open-source GPU libraries
Present technical contributions at industry conferences (e.g., NVIDIA GTC, AWS re:Invent)

Skills

CUDA

PTX assembly

GPU kernels

matrix multiplications

attention mechanisms

mixture-of-experts

memory coalescing

warp-level programming

tensor core acceleration

compute/memory overlap

Baseten

Platform for deploying and managing ML models

About Baseten

Baseten provides a platform for deploying and managing machine learning (ML) models, aimed at simplifying the process for businesses. Users can select from a library of open-source foundation models and deploy them with just two clicks, making it easier to implement ML solutions. The platform features autoscaling, which adjusts resources based on demand, and comprehensive monitoring tools for tracking performance and troubleshooting. A key differentiator is Baseten's open-source model packaging framework, Truss, which allows users to package and deploy custom models easily. The company operates on a usage-based pricing model, where clients pay only for the time their models are actively deployed, helping them manage costs effectively.

San Francisco, CaliforniaHeadquarters

2019Year Founded

$58.4MTotal Funding

SERIES_BCompany Stage

AI & Machine LearningIndustries

51-200Employees

Benefits

💰 Competitive compensation: We aim to provide 90th percentile (or better) salaries and equity grants for every team member commensurate with their experience.

🌎 Remote-first work environment: The Baseten team is welcome to work from wherever they want; fully remote, in our San Francisco office, or a mix of both. We provide a $1,000 stipend for you to make your home office comfortable and productive.

🏓 Regular in-person team summits: We get together as a team three times a year to plan, workshop, and most importantly, get to know each other better.

🌴 Unlimited PTO: We ask that everyone take at least 4 weeks of vacation. And we have a company-wide break between Christmas and New Year's Day.

🏥 Full healthcare coverage: Medical, dental and vision insurance for you and your family.

🍼 Paid parental leave: 16-weeks fully paid parental leave (adoptive and non-birth parents included) and flexibility with schedules while returning to work.

📈 401(k): Company-sponsored 401(k) for you to contribute to.

🧠: Learning and development budget: We encourage you to take classes, attend conferences, and invest in your craft and we’ll cover expenses to make it happen.

Risks

Increased competition from specialized AI models tailored for specific industries.

Potential over-reliance on Google Cloud Marketplace may limit flexibility and control.

Rapid AI model development could render Baseten's offerings obsolete without continuous innovation.

Differentiation

Baseten offers a serverless backend for machine-learning applications with auto-scaling.

Truss, an open-source model packaging framework, allows seamless deployment of custom models.

Baseten's platform provides comprehensive monitoring tools for efficient model performance tracking.

Upsides

Integration with Google Cloud Marketplace boosts visibility and customer acquisition potential.

$40M Series B funding enhances Baseten's platform capabilities and market reach.

Chains framework positions Baseten for complex AI workflows, attracting sophisticated projects.

Land your dream remote job 3x faster with AI

Try Jobo Free