Senior LLM Inference Performance Engineer

AMD; Helsinki; On-site; EUR 90,000 - 130,000; Full time

Job summary

AMD in Helsinki is seeking an experienced AI performance engineer to optimize production AI services within the AIM ecosystem, focusing on latency, throughput, and deployment configurations across diverse hardware. You will work with state-of-the-art AI tooling, design scalable measurement methodologies, and contribute to tooling that enhances developer and user experience.

A strong background in Python, Bash, Docker, Kubernetes, and Helm is required, with a degree in CS/CE/EE and a passion for

Qualifications

• Bachelor’s or Master’s degree in computer science, computer engineering, electrical engineering, or an equivalent field.
• Seasoned in deploying LLMs and other AI model types in production using frameworks like vLLM, SGLang, or similar tooling.
• Deep knowledge about LLM serving and performance metric evaluation.
• Comfortable with Python software development and bash scripting.
• Experience with Docker, Kubernetes and Helm.

Responsibilities

• Measure, analyze, and optimize LLM and AI service performance across latency and throughput for various training and inference use cases.
• Design and develop tooling to measure and analyze the performance of AI model deployments and the effect of different configurations and infrastructure, standalone and Kubernetes clusters.
• Develop and maintain internal tooling to support LLM and AI performance tuning at scale.

Skills

Python development

bash scripting

collaboration

learning agility

Education

Bachelor’s or Master’s in CS/CE/EE

Tools

Docker

Kubernetes

Helm

vLLM

SGLang

CUDA

Job description

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

The focus of this role is on the performance analysis and optimization of production grade AI services; in particular, in the AMD Inference Microservice (AIM) ecosystem. You will be part of a diverse and ambitious team responsible for ensuring reliable performance of various AI microservices on diverse hardware configurations. You will work with state-of-the-art AI tooling and models on cutting edge AI infrastructure. This role requires both deep understanding of LLMs as well as hands-on knowledge of AI tooling like inference servers.

KEY RESPONSIBILITIES

LLM and AI Performance

• Measure, analyze, and optimize LLM and AI service performance across metrics like latency and throughput for various training and inference use cases.
• Design and implement methodologies for measuring model performance, and automating optimization strategies to identify optimal configurations
• Stay on top of current advances in AI, models, APIs, and open-source ecosystems, and translate them into scalable solutions

LLM and AI Tooling

• Design and develop tooling to measure and analyze the performance of AI model deployments and the effect of different configurations and infrastructure, standalone and Kubernetes clusters.
• Develop and maintain tooling for interacting with different ecosystem functions to improve developer and user experience.
• Develop and maintain internal tooling to support LLM and AI performance tuning at scale

EXPERIENCE & KEY QUALITIES

• Seasoned in deploying LLMs and other AI model types in production using frameworks like vLLM, SGLang, or similar tooling.
• Deep knowledge about LLM serving and performance metric evaluation
• Comfortable with Python software development and bash scripting.
• Experience with Docker, Kubernetes and Helm.
• Desire and ability to continuously learn in a fast-changing environment
• Initiative, pragmatic problem solving, and great collaboration skills
• Bachelor’s or master’s degree in computer science, computer engineering, electrical engineering, or an equivalent field

NICE TO HAVE

• Experience with multi-objective hyper-parameter optimization
• Knowledge of GPU architecture, kernel development, and debugging (C/C++/CUDA). Seasoned in deploying LLMs and other AI model types in production using frameworks like vLLM, SGLang, or similar tooling, Deep knowledge about LLM serving and performance metric evaluation, Comfortable with Python software development and bash scripting, Experience with Docker, Kubernetes and Helm, Bachelor’s or master’s degree in computer science, computer engineering, electrical engineering, or an equivalent field