Edge AI Staff Engineer (9745)

Extreme Networks; Ontario; On-site; CAD 90,000 - 150,000; Full time

Job summary

Join a global leader in networking solutions as an Edge AI Staff Engineer. In this pivotal role, you'll leverage your expertise in GPU/TPU acceleration to shape cutting-edge AI solutions for edge computing. Collaborate with cross-functional teams to enhance AI inference models, ensuring real-time performance on embedded devices. This innovative firm values inclusion and fosters a positive work environment, making it an exciting time to contribute to transformative projects. If you're passionate about AI and eager to make a significant impact, this opportunity is perfect for you.

Qualifications

• 5+ years experience in AI model development, focusing on edge computing.
• Strong programming skills in Python and C++, with GPU/TPU acceleration expertise.

Responsibilities

• Lead design and architecture of Edge AI solutions with GPU/TPU acceleration.
• Develop and optimize AI inference models for edge devices.

Skills

AI model development

GPU/TPU acceleration

Python

C++

problem-solving

analytical skills

Education

Bachelor’s degree in Computer Science

Master’s degree in a related field

Tools

CUDA

Vulkan

OpenCL

LLM frameworks

deep learning libraries

Job description

Over 50,000 customers globally trust our end-to-end, cloud-driven networking solutions. They rely on our top-rated services and support to accelerate their digital transformation efforts and deliver unprecedented progress. With double-digit growth year over year, no provider is better positioned to deliver scalable outcomes than Extreme.

Inclusion is one of our core values and in our DNA. We are committed to fostering an inclusive workplace that embraces our differences and creates an atmosphere where all our employees thrive because of their differences, not in spite of them.

Become part of Something big with Extreme! As a global networking leader, learn why there’s no better time to join the Extreme team.

Job Description:

We are seeking a talented Edge AI Staff Engineer with specialized expertise in GPU/TPU acceleration to join our team. The ideal candidate will have extensive hands-on experience in local Large Language Models (LLM) inference with embedded GPU/TPU architectures. As Staff Engineer specializing in Edge AI, you will play a crucial role in shaping the future Edge AI solution, leveraging the power of GPU/TPU acceleration and enterprise grade, large scale edge compute.

The successful candidate will combine technical excellence with effective leadership, creating a positive impact on both projects and team dynamics.

Key Responsibilities

• High-Level Design and Architecture
• Influence the Edge AI strategy by providing expert advice on design and architecture.
• Make critical decisions regarding technical directions, scalability, and system performance.
• Develop and optimize AI inference models for deployment on edge devices with embedded GPU/TPU accelerators, focusing on local Low Latency Model (LLM) inference.
• Implement and fine-tune low-latency model inference pipelines to meet real-time performance requirements.
• Collaborate with cross-functional teams to integrate AI inference solutions into edge computing platforms and applications.
• Collaborate with the GPU Hardware Design Team to design and optimize GPUs that power next-generation devices.
• Conduct performance profiling and optimization to maximize the efficiency of GPU/TPU acceleration for local LLM inference.
• Work on micro-architecture development, ensuring efficient execution of graphics, compute, and AI workloads within energy and area constraints.
• Stay current with advancements in GPU/TPU technologies and edge AI frameworks, incorporating them into solution designs as appropriate.
• Provide technical expertise and support to project teams, ensuring successful implementation and deployment of edge AI solutions.

Team Leadership:

• Lead and inspire a team of engineers, providing guidance, setting goals, and ensuring collaboration.
• Oversee project planning, execution, and delivery, ensuring alignment with business objectives.
• Manage all phases of technical projects, from conception to completion.
• Develop project specifications, track progress, and control costs.
• Foster a positive work environment, encouraging professional growth and knowledge sharing.

Qualifications:

• Bachelor’s degree in computer science, Engineering, or a related field; Master’s degree preferred.
• 5+ years of hands-on experience in AI model development and deployment, with a focus on edge computing and local LLM inference.
• Strong programming skills in languages such as Python and C++.
• Proficiency in LLM frameworks (e.g., vLLM, Text generation inference, OpenLLM, Ray Serve and HuggingFace Transformers) and deep learning libraries.
• Extensive experience with GPU/TPU acceleration for AI inference, including optimization techniques (tensor, pipeline, data, sharded data parallelism) and performance tuning.
• Hands-on experience with one or more GPU frameworks: CUDA, Vulkan, OpenCL.
• Deep knowledge of GPU memory layout, familiarity with NVIDIA Jatison, ARM Mali or relevant SoC configurations.
• Knowledge of parallel computation, memory scheduling, and structural optimization.
• Excellent problem-solving and analytical skills, with a passion for innovation and continuous learning.

Additional Skills (Preferred):

• Experience with edge device hardware and software integration.
• Familiarity with edge computing architectures and IoT platforms.
• Experience with edge AI applications in domains such as robotics, autonomous vehicles, or industrial automation.

Extreme Networks, Inc. (EXTR) creates effortless networking experiences that enable all of us to advance. We push the boundaries of technology leveraging the powers of machine learning, artificial intelligence, analytics, and automation. Over 50,000 customers globally trust our end-to-end, cloud-driven networking solutions and rely on our top-rated services and support to accelerate their digital transformation efforts and deliver progress like never before. For more information, visit Extreme's website or follow us on Twitter, LinkedIn, and Facebook.

We encourage people from underrepresented groups to apply. Come Advance with us! In keeping with our values, no employee or applicant will face discrimination/harassment based on: race, color, ancestry, national origin, religion, age, gender, marital domestic partner status, sexual orientation, gender identity, disability status, or veteran status. Above and beyond discrimination/harassment based on “protected categories,” Extreme Networks also strives to prevent other, subtler forms of inappropriate behavior (e.g., stereotyping) from ever gaining a foothold in our organization. Whether blatant or hidden, barriers to success have no place at Extreme Networks.