Software - Software Engineer (ModelSys)
Seoul, South Korea (On-site)
About the Job
FuriosaAI is seeking a Software Engineer to join our ModelSys (Model Design & Optimization for Systems) team.
This team specializes in designing and optimizing AI models tailored to the architectural characteristics of FuriosaAI’s Tensor Contraction Processor (TCP).
ModelSys team is responsible for model architecture design and implementation, hardware-aware optimization, model validation, and benchmark.
These efforts directly contribute to the development of FuriosaAI’s software development kit (SDK), empowering developers to efficiently deploy optimized AI models on the FuriosaAI platform.
We’re looking for engineers who are passionate about building efficient, production-grade implementations of LLMs, diffusion models, and other state-of-the-art AI architectures—purpose-built for FuriosaAI systems
Responsibilities
Develop and optimize state-of-the-art deep neural network (DNN) models within DNN frameworks (e.g., PyTorch) for FuriosaAI's Tensor Contraction Processor (TCP) architecture.
Maintain and improve DNN model implementations and deliver as a part of Furiosa SDK.
Conduct research on generative AI models and serving optimization techniques to improve performance and efficiency.
Collaborate closely with compiler, algorithm, and platform teams to optimize models and enable efficient quantization
Minimum Qualifications
Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent industry experience.
3+ years of hands-on experience with Python programming.
Experience in developing machine learning (ML) and/or deep neural network (DNN) models at scale using DNN frameworks (e.g., PyTorch).
Research experience in machine learning, deep learning, natural language processing (NLP), and/or generative AI models.
Strong communication skills with the ability to collaborate effectively across cross-functional teams.
Preferred Qualifications
Experience in deploying and optimizing large-scale ML models in production environments.
Proven expertise in designing and implementing robust testing frameworks, with a deep understanding of testing methodologies.
Strong theoretical background in machine learning, generative AI, and model evaluation techniques.
Demonstrated contributions to open-source AI/ML projects