Lemurian Labs revolutionizes AI development with a flexible compute platform that eliminates vendor lock-in, enabling efficient, cost-effective solutions across any hardware.
Santa Clara, California
Lemurian Labs is a software-first, hardware-agnostic AI platform that simplifies development by enabling organizations to write once and deploy anywhere across CPUs, GPUs, accelerators, and edge. We help companies lower costs, boost efficiency, and scale sustainably in the post-Moore’s Law era. Discover how we are making AI accessible to all: lemurianlabs.com.
Remote · Santa Clara, California, United States, Toronto, Ontario, Canada, United States
You will design and implement compiler frontend components, including lexers, parsers, and ASTs, while managing memory through a proprietary automatic reference counting system. Additionally, you will collaborate on the full software engineering lifecycle and develop clear diagnostic tools to assist users in resolving program errors.
On-site · Toronto
You will design and implement the graph optimization layer of a heterogeneous AI compiler, focusing on transformations like operator fusion and layout propagation. You will also analyze performance data to drive improvements in throughput and latency while collaborating with front-end and backend teams.
On-site · Toronto
You will design and build developer tools for profiling, debugging, and performance introspection across the compiler stack. Additionally, you will create client-side tooling that transforms server-side compiler telemetry into actionable insights for engineers.
On-site · Toronto
Design, develop, and maintain a multi-target runtime for an AI compiler stack to ensure efficient execution across diverse hardware. Collaborate with compiler and product teams to analyze performance bottlenecks and implement advanced parallelization techniques.
On-site · Toronto
You will design and maintain the ingestion layer of a high-performance AI compiler, handling parsing, validation, and IR lowering. You will also collaborate with optimization teams to ensure operator coverage and clean IR generation across various ML frameworks.
On-site · Toronto
You will design and build core code generation capabilities for a high-performance, portable AI compiler. This involves translating high-level machine learning computations into optimized machine code for heterogeneous hardware targets.
