Software Core Development Engineer

WHAT YOU DO AT AMD CHANGES EVERYTHING 

At AMD, our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers, to PCs, gaming and embedded systems. Grounded in a culture of innovation and collaboration, we believe real progress comes from bold ideas, human ingenuity and a shared passion to create something extraordinary. When you join AMD, you’ll discover the real differentiator is our culture. We push the limits of innovation to solve the world’s most important challenges—striving for execution excellence, while being direct, humble, collaborative, and inclusive of diverse perspectives. Join us as we shape the future of AI and beyond.  Together, we advance your career.  

THE ROLE:

AMD’s Custom Software Engineering (CSE) team is hiring for a motivated individual specialized in software debug/development with area primary focus in AI solution debug and optimization and secondary responsibility in software debug related to graphics kernel mode driver in Windows.  You will be part of a dynamic and collaborative team working with the very latest hardware and software technologies on desktop and mobile platforms to help enable and optimize end-to-end AI implementation performance as well as debug reported software issues related to kernel driver.  This is an exciting opportunity to get hands-on with prototype hardware and latest graphics products/features, leverage leading edge AI frameworks and tools, apply advanced Windows debug techniques to diagnose problems, and have ability to drive improvements to overall software quality.

THE PERSON:

The ideal candidate should be passionate about software engineering and problem solving and possess leadership skills to drive sophisticated issues to resolution.  You are systems and data-minded who can thrive in a fast-paced work environment with deep troubleshooting and advanced debug experience ideally in display and/or kernel driver.  You are able to communicate effectively and work optimally with different stakeholder teams across AMD (including SWAEs, developers, PMs, and validation).  Experience in AI model integrations and optimization would be preferred skillset to contribute to the team’s AI acceleration engagements.

KEY RESPONSIBILITIES:

• Primary - Debug and triage AI model performance issues and defects across the full software stack (model, framework, runtime, compiler, drivers, firmware) on AMD hardware; reproduce issues and drive investigations to resolution.
• Profile model execution on AMD AI accelerators (e.g. GPUs and NPUs), identify latency, throughput and memory bottlenecks, and propose targeted fixes and mitigations.
• Optimize performance for inference on AMD GPUs, including as applicable parallelization strategies, quantization techniques, serving orchestration, network communication and distributed execution.
• Secondary - apply advanced software debug skills to advise or drive to closure issue investigations related to kernel driver.
• Work closely with other team members to understand design architecture and to propose solutions to fix/workaround issues or enhance product
• Stay informed of software and hardware trends and innovations, especially pertaining to algorithms and architecture in AI solutions as well as kernel driver space
• Develop technical relationships with peers, architecture specialists, and partners.
• Share subject matter expertise to working team.

• Develop AI tools and solutions for proof of concept or technical demonstrations

PREFERRED EXPERIENCE:

• Strong object-oriented programming background, Python, C/C++ preferred
• Ability to write and debug high quality code with keen attention to detail
• Effective skills in software debug, root cause analysis, workaround/fix implementation
• Knowledge of software development environments and methodologies

• Hands-on experience with NLP, LLMs, deep learning, or computer vision.

• Experience with AI performance analysis tools or profiling frameworks
• Familiarity with AI Frameworks (e.g. ONNX, PyTorch)
• Familiarity with GPU programming models (e.g. HIP, OpenCL, ROCm)
• Familiarity with ROCm ecosystem and tools is highly desirable
• Understanding of GPU architecture and system-level performance concepts
• Solid understanding in graphics kernel driver features and functionality
• Windows OS architecture knowledge relating to kernel subsystem
• Windows debug methodologies
• Experience with modern concurrent programming and threading APIs

• Experience with software development processes and tools such as debuggers, source code control systems (GitHub) and profilers is a plus 
• Should possess effective problem-solving, critical thinking, time management, and prioritization skills.
• Detailed oriented and self-driven with a strong sense of pride and ownership. 

ACADEMIC CREDENTIALS: 

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

#LI-TB1

#LI-Hybrid

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.

AMD may use Artificial Intelligence to help screen, assess or select applicants for this position.  AMD’s “Responsible AI Policy” is available here.

This posting is for an existing vacancy.