TPU Kernel Engineer
Nice to have's
Job description
About the Position
TPU Kernel Engineer
San Francisco, CA | New York City, NY | Seattle, WA
About Anthropic
Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.
About the Role
As a TPU Kernel Engineer, you'll be responsible for identifying and addressing performance issues across many different ML systems, including research, training, and inference. A significant portion of this work will involve designing and optimizing kernels for the TPU. You will also provide feedback to researchers about how model changes impact performance. Strong candidates will have a track record of solving large-scale systems problems and low-level optimization.
Responsibilities
- Design and optimize kernels for TPUs
- Identify and address performance issues in ML systems
- Provide feedback to researchers on model changes and performance
- Collaborate with the team to build safe and beneficial AI systems
Requirements
- Significant experience optimizing ML systems for TPUs, GPUs, or other accelerators
- Results-oriented with a bias towards flexibility and impact
- Ability to pick up slack, even if it goes outside your job description
- Enjoy pair programming
- Interest in learning more about machine learning research
- Care about the societal impacts of your work
Nice to Have
- Experience with high performance, large-scale ML systems
- Designing and implementing kernels for TPUs or other ML accelerators
- Deep understanding of accelerators, e.g. a background in computer architecture
- Knowledge of ML framework internals
- Experience with language modeling using transformers
Representative Projects
- Implement low-latency, high-throughput sampling for large language models
- Adapt existing models for low-precision inference
- Build quantitative models of system performance
- Design and implement custom collective communication algorithms
- Debug kernel performance at the assembly level
We Offer
- Competitive salary range: $280,000-$850,000 USD
- Location-based hybrid policy: Expected to be in one of our offices at least 25% of the time
- Visa sponsorship available
- Comprehensive benefits package
- Flexible working hours
- Generous vacation and parental leave
About the Company
Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, and a lovely office space in which to collaborate with colleagues. We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. We strive to include a range of diverse perspectives on our team.
Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links-visit anthropic.com/careers directly for confirmed position openings.
© Label Your Data. This job description was sourced from the employer's public career page. TheJob is not the employer — we index the posting and route candidates to the source. All content rights and hiring decisions belong to the employer.
Label Your Data provides secure and high quality data annotation services for Computer Vision or NLP applications since 2020. We help Data Scientists and AI Engineers streamline the dataset labeling and focus on model development.About Label Your Data:— Founded in 2020;— 200+ annotation experts in Europe, LATAM and Africa;— 98%+ annotation accuracy benchmark;— 55 supported languages;— PCI/DSS certified;— ISO/IEC 27001:2013 certified;— GDPR, CCPA and HIPAA-compliant;— HQs in North America, EU and Asia.Our experience spans over 20 industries including Automotive, Robotics, Agriculture, E-commerce, Retail, Healthcare, Manufacturing, Fintech and Insurance.Our core services include but are not limited to:— Image & video annotation: 2D boxes, OCR, object/action detection, polygons, key points, semantic segmentation, 3D cuboids;— Text annotation: classification, NER, intent & sentiment analysis, prompts creation, Q&A pairs generation;— Audio annotation: transcription, sentiment recognition;— Sensor data annotation;— Data classification & categorization;— Data entry;— Data collection;— Model validation.