OctoAI is a leading startup in the fast-paced generative AI market. Our mission is to empower businesses to build differentiated applications that delight customers with the latest generative AI features.

Our platform, OctoAI, delivers generative AI infrastructure to run, tune, and scale models that power AI applications. OctoAI makes models work for you by providing developers easy access to efficient AI infrastructure so they can run the models they choose, tune them for their specific use case, and scale from dev to production seamlessly. With the fastest foundation models on the market (including Llama-3, Stable Diffusion, and SDXL), integrated customization solutions, and world-class ML systems under the hood, developers can focus on building apps that wow their customers without becoming AI infrastructure experts.

Our team consists of experts in cloud services, infrastructure, machine learning systems, hardware, and compilers as well as an accomplished go-to-market team with diverse backgrounds. We have secured over $130M in venture capital funding and will continue to grow over the next year. We're based largely in Seattle but have a remote-first culture with people working all over the US and elsewhere in the world.

We dream big but execute with focus and believe in creativity, productivity, and a balanced life. We value diversity in all dimensions and are always looking for talented people to join our team!

Overview:

Our Automation team specializes in developing the most efficient engine for generative model deployment. We concentrate on enhancements from detailed GPU kernel adjustments to broader system-level optimizations, including continuous batching.

We are seeking a highly skilled and experienced Machine Learning Systems Engineer with experience in CUDA Kernel optimization to join our dynamic team. In this role, you will be responsible for driving significant advancements in GPU performance optimizations and contributing to cutting-edge projects in AI and machine learning.

Responsibilities:

Develop and optimize high-performance computing kernels with a focus on GPU acceleration
Implement and enhance programming solutions in C/C++ and Python.
Deep dive into GPU performance optimizations to maximize efficiency and speed.
Work on kernel optimizations specifically for CUDA or other accelerators.
Collaborate with the team to extend and improve existing machine learning compilers or frameworks such as TVM, MLIR, Pytorch, Tensorflow, ONNX Runtime, TensorRT. (This is optional but beneficial)

What we look for:

Bachelor's, Master’s or PhD’s degree in Computer Science, Electrical Engineering, or a related field.
Strong programming skills in C/C++ and Python.
Deep understanding and experience in GPU performance optimizations.
Extensive experience with kernel optimizations on CUDA or other accelerators.
Extensive experience contributing to innovative OSS/closed source projects like Cutlass, FlashAttention, FlashInfer, mlc-llm, vllm.
(Optional but preferred) Experience with machine learning compilers or frameworks such as TVM, MLIR, Pytorch, Tensorflow, ONNX Runtime, TensorRT.

Our base salary ranges are based on paying competitively for our company's size and industry and are one part of the total compensation package that also includes annual bonuses, equity, benefits, and other opportunities at OctoAI. In accordance with pay transparency laws, OctoAI is required to provide a reasonable estimate of the compensation range for this role. Individual pay decisions are ultimately based on a number of factors, including qualifications for the role, experience level, skillset, geography, and balancing internal equity. This is a reasonable estimate of the current salary base range. We expect most candidates to fall in the middle of the range. We also believe that your personal needs and preferences should be taken into consideration, so we allow some choice between equity and cash.

We recognize that people come with experience and talent beyond just the technical requirements of a job. If your experience is close to what you see listed here, please still consider applying. Diversity of experience and skills combined with passion is a key to innovation and excellence. Therefore, we encourage people from all backgrounds to apply to our positions. Please let us know if you require accommodations during the interview process.

Diversity & Inclusion:

Our mission extends beyond technological breakthroughs; we aim to mirror the diverse world we serve. We understand the unique insights, creativity, and perspectives a diverse team can bring, and we're actively seeking to broaden our horizons. As we look to the future, we aim to address our current diversity gaps and set new industry standards for inclusivity.

Benefits Our Team Enjoys:

• Comprehensive Healthcare: Fully covered premiums for employees and their dependents, including Medical, Dental, Vision, Life Insurance, and Disability Insurance.

• Competitive Compensation: A mix of salary, bonuses, and meaningful stock options.

• Financial Benefits: Flexible Spending Accounts for healthcare and dependent care, as well as a Health Savings Account for those opting for a high deductible plan.

• Future Planning: 401(k) options.

• Flexible Work Options: Remote and teleworking capabilities.

• Work-Life Balance: Flexible work hours, generous time off policies, company-sanctioned downtime twice a year, and company-paid holidays.

• Parental Benefits: Comprehensive parental leave plans for all new parents.

• Volunteer Time Off (VTO): Four days a year to give back and make a difference in communities.

• Additional Leaves: Including disability, paid family medical leave, and paid military leave.

At OctoAI, we believe in creating an environment where everyone is valued and respected. Discrimination doesn't have a place in our culture. We evaluate individuals based on their abilities and effectiveness. We're committed to equal opportunity and ensuring that all qualified applicants receive consideration, free from biases related to race, color, religion, gender, identity, orientation, national origin, genetics, disability, age, or veteran status.

Salaried, full-time Machine Learning & Modeling jobs

Staff MLSys Engineer - Kernel Optimization