Sr to Principal Machine Learning Engineer, Framework & Performance

Qualcomm; Markham; On-site; CAD 120,000 - 180,000; Full time

Job summary

Qualcomm Canada ULC in Markham is seeking a senior engineer to develop ML/AI compilers for efficient mappings of ML workloads on Qualcomm hardware. You will work on production and exploratory versions, collaborating with hardware and software teams.

The role emphasizes performance and power trade-offs, pre-silicon predictions, and close study of ML network trends, with hands-on work in C++, Python, and modern tooling.

Qualifications

• Bachelor's degree with 8+ years in hardware/software/systems.
• Proven ability to learn and adapt in fast-changing environments.
• Strong problem-solving and debugging skills.
• Experience with ML/AI compiler development preferred.

Responsibilities

• Develop and evolve ML/AI compilers for efficient mappings of ML workloads on HW.
• Analyze ML workloads to drive future ML HW/SW features.
• Define algorithms for compiling ML workloads to achieve high performance and low power.
• Collaborate across cross-site, cross-functional teams.
• Create performance-driven simulations (C++, Python) for HW/SW algorithms.
• Pre-silicon prediction of performance for ML algorithms.
• Investigate and propose improvements to tackle bottlenecks.

Skills

Problem solving

Analytical thinking

Strong communication

Detail oriented

Education

Bachelor's degree in Computer Science, Engineering, Information Systems, or related field

Master's degree in Computer Science, Engineering, Information Systems, or related field

PhD in Computer Science, Engineering, Information Systems, or related field

Tools

C++

Python

Docker

Git

Jenkins

clang/MSVC

PyTorch

ONNX

Job description

Company:

Qualcomm Canada ULC

Job Area:

Engineering Group, Engineering Group > Machine Learning Engineering

General Summary:

Today, more intelligence is moving to end devices, and mobile is becoming the pervasive AI platform. Building on the smartphone foundation and the scale of mobile, Qualcomm envisions making AI ubiquitous- expanding beyond mobile and powering other end devices, machines, vehicles, and things.

Job Purpose & Responsibilities:

• Development and evolution of ML/AI compilers (production and exploratory versions) for efficient mappings of ML/AI algorithms on existing and future HW
• Analysis of ML/AI algorithms and workloads to drive future features in Qualcomm’s ML HW/SW offerings

Key Responsibilities:

• Contributing to the development and evolution of ML/AI compilers within Qualcomm
• Defining and implementing algorithms for compiling ML/AI workloads to achieve high performance and low power on Qualcomm HW
• Creating and implementing algorithms that couple PyTorch framework efficiently to Qualcomm ML/AI Compiler flows.
• Understanding trends in ML network design, through customer engagements and latest academic research, and how this affects both SW and HW design
• Exploration and analysis of performance/area/power trade-offs for future HW and SW ML algorithms
• Creation of performance-driven simulation components (using C++, Python) for analysis and design of high-performance HW/SW algorithms on future SoCs
• Pre-Silicon prediction of performance for various ML algorithms
• Running, debugging and analyzing performance simulations to suggest enhancements to Qualcomm hardware and software to tackle framework, compute and system memory-related bottlenecks
• Successful applicants will work in cross-site, cross-functional teams.

Requirements:

• Demonstrated ability to learn, think and adapt in fast changing environment
• Detail-oriented with strong problem-solving, analytical and debugging skills
• Strong communication skills (written and verbal)
• Strong background in algorithm development and performance analysis is essential

The following experiences would be significant assets:

• Strong object-oriented design principles
• Strong knowledge of C++
• Strong knowledge of Python
• Experience in compiler, CPU, DSP and/or GPU design and development is an asset
• Knowledge of network model formats/platforms (eg. PyTorch, ONNX) is a strong asset
• Knowledge of software development processes (revision control, CD/CI, etc.)
• Familiarity with tools such as git, Jenkins, Docker, clang/MSVC
• On-silicon debug skills of high-performance compute algorithms
• Knowledge of algorithms and data structures
• Knowledge of computer architecture, digital circuits and event-driven transactional models/simulators

Minimum Qualifications:

• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 8+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.
• OR
• Master's degree in Computer Science, Engineering, Information Systems, or related field and 7+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.
• OR
• PhD in Computer Science, Engineering, Information Systems, or related field and 6+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.

Applicants:

Qualcomm is an equal opportunity employer. If you are an individual with a disability and need an accommodation during the application/hiring process, rest assured that Qualcomm is committed to providing an accessible process. You may e-mail [e-mail] or call Qualcomm's toll-free number found here. Upon request, Qualcomm will provide reasonable accommodations to support individuals with disabilities to be able participate in the hiring process. Qualcomm is also committed to making our workplace accessible for individuals with disabilities. (Keep in mind that this email address is used to provide reasonable accommodations for individuals with disabilities. We will not respond here to requests for updates on applications or resume inquiries).

Qualcomm expects its employees to abide by all applicable policies and procedures, including but not limited to security and other requirements regarding protection of Company confidential information and other confidential and/or proprietary information, to the extent those requirements are permissible under applicable law.