Software Engineer Compiler Front End
FuriosaAI is a South Korean AI semiconductor company building energy-efficient inference accelerators, servers, and software for enterprise and cloud AI deployments.
Funding history
Investors
About FuriosaAI
FuriosaAI develops the RNGD AI inference accelerator and NXT RNGD Server, alongside a software toolchain for compiling, optimizing, and deploying LLM and agentic-AI workloads.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will build compiler front-end pipelines that translate deep learning models into internal representations. You will develop graph optimizations, design extensible model-ingestion systems and kernel-language interfaces, establish verification mechanisms, and refine the language using real-world feedback.
Requirements
- Bachelor's degree in Computer Science, Mathematics, or a related field
- Experience or familiarity with compilers or program transformation systems
- Understanding of PyTorch, TensorFlow, ONNX, and model representations
- Ability to create consistent user-facing programming interfaces from complex constraints
- Python proficiency and experience with Rust or C++
Responsibilities
- Design and implement model-ingestion pipelines from deep learning frameworks into internal IR
- Develop graph-level optimizations including operator fusion, constant folding, shape inference, and layout transformations
- Build extensible ingestion structures for new model architectures and custom operators
- Design and evolve a tensor-level kernel language and user interface
- Establish verification mechanisms for translation correctness
- Collaborate to improve end-to-end compilation quality and language design