About the role
Job description:
The Qualcomm Cloud Computing team is developing hardware and software for machine learning solutions spanning the data center, edge, infrastructure, and automotive market. We are seeking ambitious, bright, and innovative engineers with experience in machine learning framework development. Job activities span the whole product life cycle from early design to commercial deployment. The environment is fast-paced and requires cross-functional interaction daily, so good communication, planning, and execution skills are a must.
Key Responsibilities:
- Analyze software requirements, determine the feasibility of design within the given constraints, consult with architecture and hardware engineers, and implement software solutions best suited for Qualcomm's SoCs.
- Analyze and identify system-level issues, interface with the software development, integration, and test teams.
- Lead high-performing teams towards system design and deliverables.
- Proven track record of leading teams in machine learning software engineering.
- Strong foundation of mathematical modeling of problems and linear algebra, coupled with state-of-the-art algorithms in the ML/AI space.
- Improve and optimize key deep learning models on Qualcomm AI 100.
- Build deep learning framework extensions for Qualcomm AI 100 in upstream open-source repositories.
- Collaborate and interact with internal teams to analyze and optimize training and inference for deep learning.
- Build software tools and ecosystem around AI software stack.
- Work on vLLM, Triton, ExecuTorch, Inductor, and TorchDynamo to build abstraction layers for inference accelerator.
- Optimize workloads for both scale-up (multi-SoC) and scale-out (multi-card) systems.
- Optimize the entire deep learning pipeline including graph compiler integration.
- Apply knowledge of software engineering best practices.
Desirable Skills and Aptitudes:
- Deep learning experience or knowledge in LLMs, natural language processing, vision, audio, and recommendation systems.
- Knowledge of the structure and function of different components of PyTorch and TensorFlow software stacks.
- Excellent C/C++/Python programming and software design skills, including debugging, performance analysis, and test design.
- Ability to work independently, define requirements and scope, and lead your own development effort.
- Well versed with open-source development practices.
- Strong developer with a research mindset who strives to innovate.
- Avid problem solver who can find solutions to key engineering and domain problems.
- Knowledge of tiling and scheduling a machine learning operator is a plus.
- Experience in using C++14 advanced features.
- Experience of profiling software and optimization techniques.
- Hands-on experience writing SIMD and/or multi-threaded high-performance code is a plus.
- Experience with ML compiler and auto-code generation using MLIR is a plus.
- Experience running workloads on large-scale heterogeneous clusters is a plus.
- Hands-on experience with CUDA and cuDNN is a plus.
Qualifications:
- Bachelor's, Master's, or PhD degree in Engineering, Machine Learning/AI, Information Systems, Computer Science, or related field.
- 10+ years of software engineering or related work experience.
- 10+ years of experience with programming languages such as C++ and Python.
Minimum Qualifications:
- Bachelor's degree in Engineering, Information Systems, Computer Science, or related field and 8+ years of software engineering or related work experience; or Master's degree in Engineering, Information Systems, Computer Science, or related field and 7+ years of software engineering or related work experience; or PhD in Engineering, Information Systems, Computer Science, or related field and 6+ years of software engineering or related work experience.
- 4+ years of work experience with programming languages such as C, C++, Java, Python, etc.