G
Quadrants: Compiler Lead
Contract type
Ongoing
Work mode
Remote
Experience
Lead / principal · Not stated
Level inferred from job title
Job description
Own the Quadrants open-source Python-to-machine-code compiler end to end, including its API, IR and lowering, optimization passes, numerical primitives, and roadmap, with CUDA as the primary target. The role aims to build the best open-source Python compiler for physics simulation and performance-critical numerical computing.
At a glance
- Work mode
- Remote
- Languages
- English
What you'll do
- Own the API and authoring experience: the surface physics and numerical-computing engineers write against, idiomatic and natural to Python users, with clean decorators, legible constraints, sharp errors, and real escape hatches
- Own the IR, lowering and backends: a stable IR that lowers to multiple backends, with room to grow and the door kept open for differentiable simulation
- Own optimization: turn naive code into strong execution plans through vectorization, register and shared-memory usage, barriers and atomics, cooperative threading, dead-buffer and redundant-traffic elimination, and dropping needless synchronization
- Own numerical primitives such as Cholesky, eigendecomposition, matmul, reductions, and solver kernels, each with its correctness, benchmarks, and regression tracking
- Watch Genesis and the compiler together, hunting for performance wins on both sides and proposing API changes that cut duplication, improve readability, and reduce platform-specific special-casing
- Treat the project as a product: benchmark real workloads, track performance over time, catch regressions early, stay close to users (Genesis first), find friction and missing abstractions, drive adoption, and set direction
What we're looking for
- GPU knowledge: what optimal looks like and why, including access patterns, registers, shared memory, barriers, atomics, and threading
- Idiomatic Python and API taste: a feel for what is natural to Python users and APIs that free users rather than constrain them
- Compiler knowledge: the path from authoring to kernels (IR, lowering, optimization), weighed against maintainability
- Reason about whole systems and have taste for where complexity should live
- Measure before optimizing, reaching for memory traffic and launch overhead before FLOPs
- Have opinions about API design
- Write tests and benchmarks as you go, not afterward
- Proactive and largely self-directed; fetch context across the company instead of waiting for it
- Comfortable talking to the engineers who use what you build and at ease designing in the open for users you will never meet
- Ready to grow into leading a small team (a couple of people, near term)
- Treat understanding as real work: read and challenge the codebase instead of just stacking features on it, and take nothing you did not write for granted
- Watch the competition and what is coming next, and bring it in and ship it
Nice to have
- CPU intuition
Your team
Quadrants
An open-source translation layer that turns ordinary Python into optimized machine code at runtime across CPU (Arm64, x86) and GPU (AMDGPU, CUDA, Metal, Vulkan) backends; a standalone project with its own roadmap, built in the open, with Genesis as its first and top-priority user.
Apply
About Genesis
Genesis, a physics simulator, is the first and top-priority user of Quadrants, the source of its hardest workloads and benchmarks.
Key facts
- Quadrants is an open-source translation layer that turns ordinary Python into optimized machine code at runtime
- Quadrants targets CPU (Arm64, x86) and GPU (AMDGPU, CUDA, Metal, Vulkan) backends, with CUDA as the primary target and x86 the strong runner-up
- The ambition is to build the best Python compiler in the world for physics and performance-critical numerical computing, intending to beat leading alternatives like Nvidia Warp, Numba, or Triton
- Quadrants is a standalone project with its own roadmap, built in the open, and general-purpose infrastructure rather than an internal tool
What they value
- Usability comes first: when usability and performance collide, usability wins unless the cost is severe
- High-performance code should feel natural to write
- Performance is the compiler's job, not the user's