Sf Tensor

Job Summary:
SF Tensor is a company focused on rethinking the software and infrastructure stack for AI and high-performance computing. They are seeking a Founding GPU Compiler Engineer to build the core compilation infrastructure for their AI compiler, optimizing models from various frameworks into binaries for large-scale AI pre-training.
Responsibilities:
• Design and implement the main compilation pipeline, from StableHLO to executable GPU and host binaries
• Build and extend MLIR dialects and passes to optimize AI workloads
• Develop backend code generation for multiple targets (NVIDIA PTX/SASS, AMD GCN/RDNA, Trainium, TPU)
• Implement classic compiler optimizations customized for large-scale training (fusion, tiling, memory planning, scheduling)
• Build search-based compiler infrastructure to explore different optimization options
• Create hybrid codegen paths for cases where direct MLIR lowering isn't practical
• Set up testing, benchmarking, and performance regression systems
• Work closely with ML researchers to understand workload characteristics and find optimization opportunities
Qualifications:
Required:
• Deep experience with compiler infrastructure (LLVM, MLIR, or similar)
• Strong background in GPU architecture and low-level optimization (CUDA, ROCm, or equivalent)
• Hands-on experience with at least one of: PTX/SASS, GCN/RDNA assembly, or other GPU ISAs
• Familiarity with ML compiler stacks (XLA, TVM, Triton, torch.compile, or similar)
• Solid systems programming skills in C++ and/or Rust
• Proven track record of building production-grade compiler infrastructure
Preferred:
• Background in distributed systems or multi-device compilation
• Contributions to open-source compiler projects
• Experience with autotuning or search-based optimization
• Familiarity with large-scale training infrastructure
• Experience with (Stable)HLO
Company:
The San Francisco Tensor Company is reinventing the software and infrastructure stack for modern AI and HPC. Founded in 2025, the company is headquartered in San Francisco, USA, with a team of 2-10 employees. The company is currently Early Stage.