About The Role
Join the inference model team dedicated to bring up the state-of-the-art models, numerically validating and accelerating new model ideas on wafer-scale hardware. You will prototype architectural tweaks, build performance-eval pipelines, and turn hard numbers into changes that land in production.
Key Responsibilities
- Prototype and benchmark cutting-edge ideas: new attentions, MoE, speculative decoding, and many more innovations as they emerge.
- Develop agent-driven automation that designs experiments, schedules runs, triages regressions, and drafts pull-requests.
- Work closely with compiler, runtime, and silicon teams: unique opportunity to experience the full stack of software/hardware innovation.
- Keep pace with the latest open- and closed-source models; run them first on wafer scale to expose new optimization opportunities.
Skills And Qualifications
- 3 + years building high-performance ML or systems software.
- Solid grounding in Transformer math—attention scaling, KV-cache, quantisation—or clear evidence you learn this material rapidly.
- Comfort navigating the full AI toolchain: Python modeling code, compiler IRs, performance profiling, etc.
- Strong debugging skills across performance, numerical accuracy, and runtime integration.
- Prior experience in modeling, compilers or crafting benchmarks or performance studies; not just black-box QA tests.
- Strong passion to leverage AI agents or workflow orchestration tools to boost personal productivity.
Assets
- Hands-on with flash-attention, Triton kernels, linear-attention, or sparsity research.
- Performance-tuning experience on custom silicon, GPUs, or FPGAs.
- Proficiency in C/C++ programming and experience with low-level optimization.
- Proven experience in compiler development, particularly with LLVM and/or MLIR.
- Publications, repos, or blog posts dissecting model speed-ups.
- Contributions to open-source agent frameworks.
