Responsibilities
- Develop and enhance ML compilers using PyTorch and C++ tailored for Qualcomm’s Neural Processing Unit (NPU) architecture.
- Design and implement advanced quantization techniques to improve model efficiency and accuracy.
- Optimize ML workloads for deployment across diverse devices, ensuring top-tier performance and energy efficiency.
- Work directly with strategic customers to address specific challenges and deliver tailored ML solutions.
- Collaborate with architecture and software engineering teams to integrate cutting-edge ML technologies into Qualcomm platforms.
- Research, prototype, and implement innovative solutions in ML compiler design and system-level optimizations.
- Evaluate and debug ML performance to identify and resolve bottlenecks in complex workflows.
- Create thorough technical documentation to share knowledge and advancements with the team. Qualifications:
- Qualifications:
- Bachelor’s or advanced degree in Computer Science, Electrical Engineering, Machine Learning, or a related discipline.
- Strong expertise in PyTorch and C++ programming.
- Experience with ML workload analysis, compiler development, and quantization techniques.
- Familiarity with deep learning frameworks such as TensorFlow or ONNX is a plus.
- Proven track record of solving complex performance and efficiency challenges in hardware-aware ML solutions.
- Ability to work collaboratively with strategic customers and deliver impactful results.
- Excellent analytical skills and ability to thrive in a high-performance team environment.
Basic qualifications
- Bachelor's degree in Science, Engineering, or related field and 2+ years of ASIC design, verification, validation, integration, or related work experience.
Preferred qualifications
- Experience with ML model deployment on hardware accelerators such as GPUs, TPUs, or NPUs.
- Understanding of system-level architecture and low-level programming.
- Contributions to ML research or publications in relevant fields are an advantage.
Tags & focus areas
Used for matching and alerts on DevFound Machine Learning Pytorch Ai