Staff Software Engineer (SIMD Kernels)
Posted Updated
- As a member of the SIMD Kernels team, you will help productize the software stack for our AI compute engine
- You will develop, enhance, and maintain software kernels for ML operators—such as softmax, layer norm, and activation functions—for next‑generation AI hardware
- You will also build solutions that make our SDK intuitive for developers to use and analyze performance
- You have experience building software kernels for modern hardware architectures and understand how to map algorithms and AI‑framework computational graphs onto those architectures
- You’re comfortable working across the full toolchain and navigating hardware–software co‑design trade‑offs
- You can deliver and scale high‑quality software quickly in a fast‑moving development environment
Benefits
- Equity
- Health care
- Flexible time-off
- Paid paternity leave
- 401k retirement plan
- Remote & hybrid working model
- Work with world-leading engineers and researchers
- On-site fitness center
- Free food and snacks
- Peer coaching & development
- Happy hours
- Team-building activities
- Experience in implementing operators commonly used in ML workloads—GEMMs, Convolutions, softmax, layer normalization, pooling, etc
- Experience in implementing algorithms in C/C++ and Python
- MS or PhD in computer engineering, math, physics, or a related degree with 5+ years of industry experience
- Strong grasp of computer architecture, data structures, system software, and machine learning fundamentals
- Self-motivated team player with a strong sense of ownership and leadership
- Experience in implementing algorithms for specialized hardware such as FPGAs, DSPs, GPUs, AI accelerators using libraries such as CUDA, etc
- Proficient in C/C++ and Python development in Linux environment and using standard development tools
- Work experience at a cloud provider or AI compute/subsystem company
- Experience working with ML compilers and algorithms, such as MLIR, LLVM, TVM, Glow, etc
- Experiences in development for embedded SIMD vector processors such as Tensilica
- Experience with a deep learning framework (such as PyTorch or TensorFlow) and ML models for CV, NLP, or recommendation
- Experience with ML frameworks such as TensorFlow and/or PyTorch
- Prior startup, small team, or incubation experience