1 year ago
Remote, United States +3 moreMid Level
Responsibilities
- Develop operator lowering, graph and IR transformations, optimization passes, and backend code generation across the compiler stack.
- Optimize compilation for dataflow architectures through pipelined scheduling, memory orchestration, and resource-constrained execution strategies.
- Collaborate with hardware architects to shape accelerator features, instruction sets, execution models, and compiler–hardware co-design.
- Develop compilation strategies that combine analog compute with digital subsystems.
- Build and maintain a compiler that produces high-performance binaries with strong debugging support, clear error messages, and predictable performance models.
Requirements
- At least 3 years of experience building compilers or high-performance systems software, particularly involving complex resource management or optimization.
- Expertise in modern C++ and strong Python skills.
- Experience with SSA-based or graph-based compiler IRs, transformations, and code generation.
- Exposure to specialized accelerators such as GPUs, NPUs, FPGAs, or custom ASICs, or to parallel architectures.
Benefits
- Opportunity to shape compilation of deep learning and LLM workloads on novel hardware.
- Role spanning software and hardware co-design, including accelerator architecture.
- Collaborative environment focused on engineering rigor, continuous integration, user-focused design, shared learning, and technical excellence.
- Competitive compensation, equity, and benefits package.
About Mythic
Mythic builds analog compute-in-memory AI processors and a compiler/runtime stack for efficient inference in edge and data-center deployments. The privately held company, founded in 2012 and headquartered in Austin, TX, sells silicon and development tools to customers in automotive, robotics, industrial, and defense markets. Investors include Honda and Lockheed Martin Ventures.