Forward Deployed Engineer - LLM Quantization
New roles land in Following.
Seoul, KoreaPosted 10 months agofulltime
Market pay check
Matched to Computer systems and software professionals
Source: Ministry of Employment and Labor wage information system (wage.go.kr), wage distribution by occupation.
What you'd do
- Develop,convert,and validate LLMs for on-device NPU deployment environments.
- Research quantization techniques and apply them across diverse LLM model architectures.
- Lead exploratory research on model optimization,including papers and patent filings.
What they want
- Hold three or more years of machine learning or data science experience,or equivalent.
- Understand deep learning and LLM fundamentals with hands-on framework experience.
- Have applied post-training quantization or quantization-aware training in production or research.
Nice to have
- Applied optimization and quantization to generative AI models including LLMs or LVMs.
- Researched on-device NPU generative AI development and quantization techniques previously.
- Published papers at top-tier AI,ML,or LLM quantization conferences or venues.
Seoulstart's read
- Visa tier (likely)
- E-7 specialty / professional (likely)
- Korean language
- Korean requirement not stated