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_
THE ROLE:
As a Senior Manager of AI Inference Engine Performance, you will lead and manage a team of highly skilled AI and ML software development engineers within the AMD Framework Department. You will be responsible for driving the optimization of AI model inference engines, focusing on GPU workload optimization and overall inference performance. This role will require a strong combination of technical expertise and leadership skills to develop and execute a roadmap that enhances scalability, flexibility, and efficiency in AI inference systems.
THE PERSON:
We are seeking someone with a deep passion for AI and machine learning performance engineering, who thrives in a fast-paced, innovative environment. The ideal candidate will be a seasoned leader with a strong technical background in AI inference, GPU kernel development, and performance optimization. A strategic thinker with a hands-on approach, you will excel in mentoring teams, collaborating across functions, and driving technical excellence across complex AI solutions.
KEY RESPONSIBILITIES:
Lead and scale a team of engineers to advance AI inference across multiple domains, ensuring optimal performance and scalability.
Define and execute a technical roadmap to enhance the flexibility, performance, and efficiency of the AI inference engine.
Collaborate closely with research, engineering, and product teams to align solutions with business goals, driving AI performance optimizations in GPU workloads.
Provide technical leadership by enforcing software engineering best practices and fostering a collaborative, high-performance culture.
Work with engineers specializing in GPU kernel development to optimize performance for deep learning AI operators.
Manage and optimize team efforts to streamline AI model serving, focusing on performance and throughput.
Develop strategies to showcase and present the technical capabilities of AMD's inference platform to internal and external stakeholders, including executives.
Stay ahead of industry trends, tracking competitive developments in inference and preparing technical responses to address market shifts.
PREFERRED EXPERIENCE:
10+ years of experience in ML model training, serving, infrastructure, or performance engineering, with 5+ years in leadership roles.
Expertise in LLM inference systems, distributed computing, and GPU kernel programming for performance optimization.
Proficiency in working with machine learning frameworks such as TensorFlow or PyTorch, and solid experience in GPU programming.
Hands-on experience in high-performance computing and optimizing workloads across heterogeneous compute clusters.
In-depth knowledge of compiler optimization and experience with tools such as LLVM and ROCm.
Proven track record of leading teams, fostering inclusivity, and driving performance improvements in both technical and cultural aspects.
Strong ability to collaborate with cross-functional teams and communicate complex technical concepts to diverse audiences, including executive leadership.
Experience working with hyperscale cloud providers and hands-on engagement in AI inferencing workflows and industry-standard serving frameworks.
A passion for staying ahead of the curve in AI/ML trends, with a track record of publishing content or presenting at industry events.
ACADEMIC CREDENTIALS:
Master's and/ PhD degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
#LI-FL1
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
Find Connections via Linkedin
