Gimlet Labs is seeking a Member of Technical Staff focused on compilers. In this role, you will work on the core compilation and lowering infrastructure that transforms high-level AI workloads into efficiently executable programs across diverse, cutting-edge hardware. You will design and implement compiler systems that partition workloads, lower them through multiple IRs, and target a range of execution runtimes and accelerators.
This is a role for engineers who enjoy building real systems, working close to hardware, and translating emerging AI models and execution patterns into production-ready infrastructure.
Responsibilities- Design and implement compiler pipelines that transform high-level AI workloads into executable programs across heterogeneous hardware
- Develop and evolve multi-level IRs spanning graph-level, tensor-level, and kernel-level representations
- Implement partitioning and lowering strategies that map workload components to the appropriate execution runtimes and accelerators
- Support both ahead-of-time and JIT compilation paths, including dynamic shapes and runtime specialization
- Integrate new model architectures, ops, and execution patterns into the compiler stack
- Work closely with runtimes, kernels, and systems to ensure correctness, performance, and scalability across the stack
Qualifications- Strong software engineering fundamentals
- Experience building or working on compiler systems or compiler-adjacent infrastructure
- Comfort reasoning about execution, memory, and performance across hardware boundaries
Preferred Qualifications- Experience with compiler frameworks such as LLVM, MLIR, TVM, XLA, or similar
- Experience designing or working with multi-level IRs
- Familiarity with hardware-specific lowering for GPUs, accelerators, or vectorized architectures
- Experience interfacing with execution runtimes, launch APIs, or memory allocators
- Software development experience in C++ and Python
