Senior Staff AI GPU Runtime Engineer

WHAT YOU DO AT AMD CHANGES EVERYTHING

We care deeply about transforming lives with AMD technology to enrich our industry, our communities, and the world. Our mission is to build great products that accelerate next-generation computing experiences – the building blocks for the data center, artificial intelligence, PCs, gaming and embedded. Underpinning our mission is the AMD culture. We push the limits of innovation to solve the world’s most important challenges. We strive for execution excellence while being direct, humble, collaborative, and inclusive of diverse perspectives. 

AMD together we advance_

THE ROLE: 

Come join our team working on the open-source SHARK, IREE, Turbine, and torch-mlir projects. You will be responsible for building (distributed) training/inference solutions and service layers on top of existing core ML compiler and runtime. There will be no short of intriguing technical challenges to tackle, and there are abundant chances to collaborate with industry experts working at different layers of the stack. If this sounds interesting to you, please don’t hesitate to reach out to us! 

THE PERSON: 

An ideal candidate should be familiar with ML model parallelism techniques, multi-GPU inference, sharding, collectives, and integrating ML compiler/runtime/libraries into ML model services. He/she should be willing to learn and work across boundaries, and comfortable with fast paced iterations to bring in the newest features in ML serving.    

KEY RESPONSIBILITIES: 

• Develop and maintain ML serving solutions on top of SHARK/IREE compiler and runtime. 
• Enable various ML model parallelism techniques on top of SHARK/IREE 
• Develop and maintain collective solutions in various GPU backends in SHARK/IREE
• Analyze whole system performance, identify bottlenecks, propose ideas to improve, prototype and productionize solutions. 
• Follow industry directions and adopt emerging technologies in model serving

PREFERRED EXPERIENCE: 

• Familiarity with various model parallelism techniques 

• Experience with existing ML model serving frameworks like vLLM, TensorRT, etc. 
• Experience with multi-GPU inference 
• Experience with collectives and communication mechanisms 
• Familiarity with SHARK, IREE, MLIR, PyTorch, etc. 
• Open-source development ethos

ACADEMIC CREDENTIALS: 

• Bachelor’s or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent 

#LI-EM1

At AMD, your base pay is one part of your total rewards package.  Your base pay will depend on where your skills, qualifications, experience, and location fit into the hiring range for the position. You may be eligible for incentives based upon your role such as either an annual bonus or sales incentive. Many AMD employees have the opportunity to own shares of AMD stock, as well as a discount when purchasing AMD stock if voluntarily participating in AMD’s Employee Stock Purchase Plan. You’ll also be eligible for competitive benefits described in more detail here.

AMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services. AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law.   We encourage applications from all qualified candidates and will accommodate applicants’ needs under the respective laws throughout all stages of the recruitment and selection process.