We believe AI will fundamentally transform how people live and work. CentML’s mission is to massively reduce the cost of developing and deploying ML models so we can enable anyone to harness the power of AI and everyone to benefit from its potential.
Our founding team is made up of experts in AI, compilers, and ML hardware and has led efforts at companies like Amazon, Google, Microsoft Research, Nvidia, Intel, Qualcomm, and IBM. Our co-founder and CEO, Gennady Pekhimenko, is a world-renowned expert in ML systems who holds multiple academic and industry research awards from Google, Amazon, Facebook, and VMware.
About the Position
We are seeking an experienced engineer to lead and own CentML’s compiler products (https://docs.hidet.org/stable/index.html). The team has been developing an open-source deep learning compiler that supports end-to-end compilation of DNN models from PyTorch and ONNX to efficient CUDA kernels. A series of graph-level and operator-level optimizations are applied to optimize the performance.
The successful candidate will play a pivotal role in shaping the future of CentML. The role entails setting technical priorities and objectives, making sure our progress is on track, and managing and growing a high-performing team.
What you’ll do
- Own and support CentML’s open-source inference compiler ensuring wide adoption by ML and System developers and researchers.
- Derive and execute strategies to set CentML’s products on a positive trajectory within the ML ecosystem and the competitive landscape.
- Develop a strategic roadmap for CentML’s compiler products by collaborating with functional leaders and senior leadership; execute the roadmap and make sure CentML’s inference products are more capable, scalable, and reliable each day.
- Build, mentor, and manage a high-performing engineering team, and foster a collaborative and inclusive work environment.
- Identify and recruit top engineering talent that accelerates the development of CentML’s products.
- Continuously optimize engineering processes, workflows, and methodologies to enhance efficiency, productivity, and quality. Implement best practices and drive a culture of continuous improvement.
What you’ll need to be successful
- Industry experience (10+ years), including several years in technical leadership roles and compiler engineering.
- Strong background in GPU programming (e.g., CUDA, CUTLASS, PTX, ROCm) for high-performance computing, machine learning, or graphics applications.
- Strong background in ML compilers (e.g., TensorRT, Dynamo & Inductor, Triton). Deep understanding of compiler design principles, optimization techniques, and code generation.
- Experience in researching or contributing to HPC/ML/DL systems, frameworks or libraries
- Proven track record of building and managing high-performing engineering teams. Ability to inspire, guide, and develop team members to achieve their potential.
- Exceptional interpersonal and communication skills, enabling effective collaboration with cross-functional teams and executive leadership.
- A solid foundation in software development practices, methodologies, and design patterns. Ability to lead technical discussions, provide guidance, and make informed decisions on complex technical issues.
Benefits & Perks
- An open and inclusive culture and work environment
- Fully stocked kitchen at the office
- Full health and dental benefits
- Parental Leave top-up for 6 months
- Continuous education budget
- Generous vacation - we’re not saying unlimited, but if you need extra time to recharge, just ask
At CentML, we celebrate our differences and value cultivating an inclusive environment for all. We welcome applications of all kinds and are committed to providing an equal opportunity process.