Member of Technical Staff - Compilers

Gimlet Labs; San Francisco (CA); On-site; USD 120,000 - 150,000; Full time

Job summary

A technology company specializing in AI infrastructure is seeking a Member of Technical Staff to design and implement compiler systems. This role involves building compiler pipelines for heterogeneous hardware while ensuring performance and scalability. The ideal candidate should have solid software engineering skills and experience in compiler systems, particularly with frameworks like LLVM or similar. This position is focused on enhancing AI workload execution efficiency to support advanced infrastructure.

Qualifications

• Experience building or working on compiler systems or compiler-adjacent infrastructure.
• Strong problem-solving skills and attention to detail.
• Ability to work close to hardware systems.

Responsibilities

• Design and implement compiler pipelines for heterogeneous hardware.
• Develop multi-level intermediate representations (IRs).
• Implement partitioning and lowering strategies for workloads.
• Support both ahead-of-time and JIT compilation paths.
• Integrate new model architectures into the compiler stack.
• Ensure correctness and performance across the stack.

Skills

Strong software engineering fundamentals

Experience with compiler systems

Comfort with execution and performance

C++ development experience

Python development experience

Tools

LLVM

MLIR

TVM

XLA

Job description

Gimlet Labs is building the first heterogeneous neocloud for AI workloads. As AI systems scale, the industry is hitting fundamental limits in power, capacity, and cost with today’s homogeneous, vertically integrated infrastructure. Gimlet addresses this by decoupling AI workloads from the underlying hardware. Our platform intelligently partitions workloads into components and orchestrates each component to hardware that best fits its performance and efficiency needs. This approach enables heterogeneous systems across multi-vendor and multi-generation hardware, including the latest emerging accelerators. These systems unlock step-function improvements in performance and cost efficiency at scale.

On top of this foundation, Gimlet is building a production-grade neocloud for agentic workloads. Customers use Gimlet to deploy and manage their workloads through stable, production-ready APIs, without having to reason about hardware selection, placement, or low-level performance optimization.

Gimlet works with foundation labs, hyperscalers, and AI native companies to power real production workloads built to scale to gigawatt-class AI datacenters.

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