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.
ResponsibilitiesHardware-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.
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.
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.
Skills Required
- Bachelor's degree in Computer Science, Mathematics, or a related technical field
- Foundational knowledge of compiler design and optimization
- Ability to abstract complex hardware/software constraints into logical algorithms
- Experience or familiarity with functional programming languages
What We Do
FuriosaAI designs and develops data center accelerators for the most advanced AI models and applications. Our mission is to make AI computing sustainable so everyone on Earth has access to powerful AI. Our Background Three misfit engineers with each from HW, SW and algorithm fields who had previously worked for AMD, Qualcomm and Samsung got together and founded FuriosaAI in 2017 to build the world’s best AI chips. The company has raised more than $100 million, with investments from DSC Investment, Korea Development Bank, and Naver, the largest internet provider in Korea. We have partnered on our first two products with a wide range of industry leaders including TSMC, ASUS, SK Hynix, GUC, and Samsung. FuriosaAI now has over 140 employees across Seoul, Silicon Valley, and Europe. Our Approach We are building full stack solutions to offer the most optimal combination of programmability, efficiency, and ease of use. We achieve this through a “first principles” approach to engineering: We start with the core problem, which is how to accelerate.
