Be part of the team creating the software foundation for next-generation AI compute platforms. In this role, you’ll work across the full stack — from low-level kernels and hardware-optimized operators to large-scale ML deployment frameworks — in close collaboration with compiler developers, ML scientists, and hardware specialists. This position offers the chance to contribute to state-of-the-art AI infrastructure, fine-tune software for custom hardware, and deepen your expertise in system software and machine learning.
Responsibilities (some of the following)
- Design, develop, and maintain components of the deployment stack and software kernels for AI compute platforms
- Optimize and implement core ML operators (e.g., GEMMs, convolutions, BLAS routines, SIMD kernels)
- Translate computational graphs from ML frameworks onto the underlying hardware
- Contribute to compiler infrastructure together with compiler and hardware teams
- Investigate and resolve issues through system-level debugging and performance analysis
- Deliver scalable software solutions under ambitious development schedules
- Define and apply practices for testing, deployment, and scaling AI systems
Minimum qualifications
- Bachelor’s degree in Computer Science, Engineering, Mathematics, or related discipline, with 3+ years of professional software development experience
- Solid knowledge of computer architecture, system software, data structures
- Strong programming skills in C/C++ or Python in Linux environments using common development tools
- Hands-on experience implementing algorithms in high-level languages (C/C++/Python)
- Exposure to specialized hardware (GPUs, FPGAs, DSPs, AI accelerators) and frameworks such as OpenCL or CUDA
- Experience designing or working with high-performance software systems
- Solid knowledge of ML fundamentals
- Motivated team player with a strong sense of responsibility
You are a great fit if you have experience in at least one of the following areas:
- Model serving frameworks (e.g., Triton Inference Server, DeepSpeed Inference, vLLM)
- Deep learning frameworks (e.g., PyTorch, TensorFlow)
- ML runtimes (e.g., ONNX Runtime, TVM, IREE, XLA)
- Distributed collectives (e.g., Gloo, MPI)
- Software testing and validation methodologies
- Deploying ML workloads (LLMs, VLMs, NLP, etc.) across distributed systems
- Implementation of ML operators and kernels (e.g., SIMD routines, Activation functions, Pooling layers, Quantization layers)
- Hardware-aware optimizations and performance tuning
- 2+ years of experience developing software targeting AI hardware
Contribution to open-source projects (e.g., LLVM, PyTorch, TensorFlow, ONNX Runtime, xDSL, IREE) is a big plus.