This role may have closed.
Listings older than 30 days are deprioritized in search. The link to the source is still below in case the posting is still open. For active openings, see similar jobs.
FuriosaAI
Software Engineer (Quantization Engineer)
Seoul, Seoul, South KoreaPosted 9 months agofulltime
What you'd do
- Develop model compression tools enabling efficient LLM quantization on FuriosaAI NPU hardware
- Acquire and validate quantized model performance across diverse AI model types
- Research and develop advanced compression algorithms beyond standard quantization techniques
What they want
- Demonstrate extensive PyTorch development experience for deep learning model implementation
- Hold experience developing commercial software products in a production environment
- Bring 3 or more years of relevant hands-on industry experience
Nice to have
- DevOps and MLOps experience and knowledge
- Experience using LLM inference tools such as vLLM or TensorRT-LLM
- Deep learning quantization experience and theoretical knowledge
Seoulstart's read
- Visa tier (likely)
- E-7 specialty / professional (likely)
- Korean language
- Korean requirement not stated
- English friendliness
- Low: Korean-language workplace
Related Seoulstart guides
Similar roles on Seoulstart
AI Research Engineer Intern (체험형)Nota AI · Seoul, South Korea · 2 days ago
Senior Back-end Engineer (Coupang Pay Core)Coupang · Seoul, South Korea · 1 day ago
Solutions ArchitectDatabricks · Seoul, South Korea · 1 day ago