FuriosaAI
FuriosaAI

Software Engineer, Compiler (Optimization)

TLDR

Design and optimize hardware-aware compiler pipelines to map tensor ops to accelerator resources for high-performance AI workloads.

About the Job

The compiler plays a central role in FuriosaAI’s mission to build high-performance, energy-efficient AI systems. Modern deep learning models are evolving rapidly and becoming increasingly diverse, making compilation a challenging problem. Transforming these models into efficient executable programs requires careful reasoning about complex transformations while preserving program meaning and structure.

In this role, your mission is defined by two primary pillars:

  • Adaptability & Enablement: We ensure that a vast diversity of model structures can be reliably mapped onto our hardware. Stable compilation in our world means designing robust mapping strategies that can handle new and evolving model architectures with consistency.

  • Extreme Efficiency & Optimization: We push the hardware to its absolute limits. This involves deeply understanding the hardware architecture to explore various execution strategies, accurately predicting their performance, and identifying the optimal path for any given workload.

We are looking for engineers who can combine rigorous program analysis with creative algorithmic problem-solving to build the world's most efficient AI engine.

Responsibilities

  • Hardware-Aware Compiler Optimization: Develop and implement optimization algorithms that map high-level tensor operations to specialized hardware resources.

  • Performance Analysis & Modeling: Build analytical models to predict execution cycles and resource contention for data-driven optimization.

  • Search-based Strategy Optimization: Develop automated mechanisms to explore and identify optimal execution strategies such as tiling and scheduling.

  • DSL & IR Design: Evolve the compiler’s lower layers to expose hardware capabilities while maintaining a programmable and consistent interface for kernel generation.

  • Reliability & Verification: Establish validation frameworks to ensure the correctness and stability of compiled kernels across various configurations.

Minimum Qualifications

  • Bachelor’s degree in Computer Science, Mathematics, or a related technical field.

  • Foundational knowledge of compiler design and optimization passes.

  • Ability to abstract complex hardware/software constraints into logical algorithms and solve problems through rigorous reasoning.

  • Experience or familiarity with functional programming languages.

Preferred Qualifications

  • Master’s or PhD in Programming Languages, Compilers, Program Analysis, or related fields.

  • Research or industry experience with compiler infrastructures like LLVM or MLIR.

  • Experience developing code generators, instruction schedulers, or high-performance kernels for specialized accelerators (NPU, GPU, etc).

  • Experience applying program analysis techniques to optimize performance or ensure program correctness.

  • Experience in designing large-scale software systems using functional programming paradigms.

Contact

  • recruit@furiosa.ai

FuriosaAI develops high-performance, energy-efficient AI semiconductor solutions designed to drive the next generation of AI inference. By focusing on disruptive technology and rapid expansion into global markets, we aim to establish ourselves as a top player in the AI infrastructure landscape.

Founded
Founded 2017
Employees
51-200 employees
Industry
semiconductors
Funding stage
Series C+
Total raised
$270M raised
View company profile

Pro members saw this job first

New jobs unlock for everyone after 24 hours. Startup Jobs Pro shows them right away, with instant alerts and salary filters. From $7/month.

Get Pro