Job Description
Job Overview:
Our vision is to transform how the world uses information to enrich life for all.
Micron Technology is a world leader in innovating memory and storage solutions that accelerate the transformation of information into intelligence, inspiring the world to learn, communicate and advance faster than ever.
The Smart Manufacturing and AI team builds advanced machine learning, GenAI, and Agentic AI solutions that directly power Micron’s manufacturing advantage. We work at the intersection of cutting‑edge AI and real‑world production systems, turning massive data and compute into measurable impact. If you enjoy solving hard problems at scale and seeing your work drive silicon to market, this is the team for you!
This role is critical to how we train, optimize, and deploy large‑scale AI systems on modern GPU platforms. As a GPU Performance Engineer, you will push the limits of multi‑GPU and distributed training, shape next‑generation AI workloads, and partner closely with data scientists, engineers, and hardware architects. Your work will directly influence performance, cost, and speed across Micron’s AI‑powered manufacturing stack.
Responsibilities:
Architect and complete large-scale custom model training and fine-tuning jobs (SFT, RLHF) on multi-node, multi-GPU clusters.
Optimize training throughput and memory efficiency using distributed training strategies (FSDP, DeepSpeed, Megatron-LM) and mixed-precision techniques (FP16/BF16).
Design and develop autonomous AI Agents capable of multi-step reasoning, planning, and tool execution to automate complex manufacturing workflows.
Analyze and profile complex workloads (e.g., LLM training, Rendering pipelines) to identify bottlenecks in compute, memory bandwidth, and latency.
Write and optimize high-performance kernels using CUDA, HIP, or custom assembly (PTX/SASS) to unlock hardware capabilities.
Collaborate with Hardware Architects to define features for next-generation GPUs based on workload characterization.
Design and implement performance regression testing suites to catch degradations in drivers or compilers.
Mentor engineers who are developing skills in parallel programming paradigms and optimization techniques.
Minimum Qualifications:
10+ years of experience with deep expertise in GPU architecture (memory hierarchy, tensor cores, NVLink) and GPU resource management across cloud and on‑prem environments, along with 5+ years in performance optimization, parallel computing, and low‑level systems using C++ and GPGPU frameworks (CUDA preferred; HIP/OpenCL/Metal acceptable).
Strong hands-on experience building scalable ML systems, including distributed training (DDP, FSDP), model parallelism, and end-to-end automation of training, testing, and deployment workflows.
Deep proficiency in LLMs, including prompt engineering, tool/function calling, chain-of-thought reasoning, fine-tuning with PEFT methods (LoRA, QLoRA), and inference optimization using engines like vLLM and TensorRT-LLM.
Experience developing GenAI applications and AI agents using frameworks such as LangChain, LangGraph, LlamaIndex, and AutoGen, with strong knowledge of ML frameworks (PyTorch required; TensorFlow/scikit-learn a plus).
Strong programming in Python (preferred) or Java, with experience in CI/CD and cloud-native tools (Git, Jenkins, Docker, Kubernetes); excellent communication skills, fast-paced delivery mentality, and a Bachelor’s or Master’s degree in Computer Science, Statistics, or a related field.
Preferred Qualifications:
Ph.D. in Computer Science, Statistics, or related field (or equivalent experience), with strong foundations in mathematics, probability, statistics, and algorithms.
Experience with HPC job schedulers (e.g., Slurm) and orchestrating large-scale GPU workloads on Kubernetes using tools such as Ray and Kubeflow.
Strong expertise in CUDA programming, Triton kernels, and developing custom C++ extensions for PyTorch to optimize and accelerate workloads.
Experience designing and coordinating multi-agent systems, including collaboration between specialized agents in complex architectures.
Proven ability to productionize data science solutions, with experience in computer vision and/or signal processing for classification and feature extraction.
As a world leader in the semiconductor industry, Micron is dedicated to your personal wellbeing and professional growth. Micron benefits are designed to help you stay well, provide peace of mind and help you prepare for the future. We offer a choice of medical, dental and vision plans in all locations enabling team members to select the plans that best meet their family healthcare needs and budget. Micron also provides benefit programs that help protect your income if you are unable to work due to illness or injury, and paid family leave. Additionally, Micron benefits include a robust paid time-off program and paid holidays. For additional information regarding the Benefit programs available, please see the Benefits Guide posted on micron.com/careers/benefits.
Micron is proud to be an equal opportunity workplace and is an affirmative action employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, age, national origin, citizenship status, disability, protected veteran status, gender identity or any other factor protected by applicable federal, state, or local laws.
To learn about your right to work click here.
To learn more about Micron, please visit micron.com/careers
For US Sites Only: To request assistance with the application process and/or for reasonable accommodations, please contact Micron’s People Organization at hrsupport_na@micron.com or 1-800-336-8918 (select option #3)
Micron Prohibits the use of child labor and complies with all applicable laws, rules, regulations, and other international and industry labor standards.
Micron does not charge candidates any recruitment fees or unlawfully collect any other payment from candidates as consideration for their employment with Micron.
AI alert: Candidates are encouraged to use AI tools to enhance their resume and/or application materials. However, all information provided must be accurate and reflect the candidate's true skills and experiences. Misuse of AI to fabricate or misrepresent qualifications will result in immediate disqualification.
Fraud alert: Micron advises job seekers to be cautious of unsolicited job offers and to verify the authenticity of any communication claiming to be from Micron by checking the official Micron careers website in the About Micron Technology, Inc.
