Back to Search Results
Get alerts for jobs like this Get jobs like this tweeted to you
Company: AMD
Location: San Jose, CA
Career Level: Entry Level
Industries: Technology, Software, IT, Electronics

Description



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_



We are looking for senior tech leader to lead effort on Shortfin Machine Learning Inference Server ! In this role you will be architecting, developing and managing work of other talented engineers to develop the best-in-calss open source inference serving software that is optimized for serving AMD data center Instinct GPUs. The serving software should be able to serve Large Language Models and Diffusion Models on single or multiple nodes and support cutting-edge optimizations such as pipeline parallelism, tensor Parallelism, disaggregated prefill & decode, chunked prefill, PagedAttention, RadixAttention. Additinally, the serving software should be able to use GPU driver and collective communciation libraries optimally to have fastest possible device to device and inference server to inference server communication for single and multiple nodes to deliver very high throughput while meeting the service level agreements such as maximum allowed latency. 

Preferred Background:
-- BS/MS/PHD in Computer Science, Computer Engineering, ECE
-- 14+ software development experience
-- Prior experience on develoiping inference software software

-- Understanding of GPU archietcture, MLIR, ML compilers
-- C++/Python coding skills
-- Prior experience with managing work and being a hands-on technical leader

 


#LI-HYBRID

#LI-DNI 



Benefits offered are described:  AMD benefits at a glance.

 

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.


 Apply on company website