This is your opportunity to join a mission-driven startup building the foundation of sustainable AI. The team is creating a high-performance compiler and runtime that allows developers to “build once, deploy anywhere”—from the cloud to the edge—while optimizing efficiency and scalability.
As a Runtime Engineer, you will focus on developing multi-target runtime systems, leveraging advanced techniques in concurrency, parallelization, and hardware optimization. Your work will directly shape the performance and accessibility of next-generation AI infrastructure.
What You Will Do
- Design, develop, and optimize multi-target runtime systems.
- Use modern techniques in parallelization and partitioning to generate highly efficient kernels.
- Rapidly prototype and explore current approaches using data-driven methods.
- Benchmark and analyze compiler outputs across diverse hardware platforms.
- Collaborate with product teams to align runtime design with ML engineers’ needs.
- Build tools to identify, analyze, and resolve performance bottlenecks.
What You Will Bring
- Strong expertise in asynchronous and concurrent programming.
- 4+ years of experience with C/C++ (C++14 or newer).
- Solid understanding of hardware architectures (vector vs scalar registers, memory hierarchies).
- Experience with OS kernel or hypervisor development.
Preferred:
- Experience with CUDA, ROCm, or GPU programming.
- Background in HPC (high-performance computing).
- Advanced degree (MS/PhD) in Computer Science or related field.
- Familiarity with deep learning frameworks (PyTorch, JAX, Triton).
- Experience programming for large compute clusters.
Compensation & Perks
- Salary: Competitive, adjusted for experience and geography.
- Equity + performance-based bonus opportunities.
- Medical, dental, and vision coverage.
- Retirement savings plan.
- Supplemental wellness benefits.
- Hybrid flexibility (SF Bay Area or Toronto).
Why Join Us?
- Build core AI infrastructure – work on runtime systems that power sustainable, scalable AI.