Opportunity
Model Compression Research Engineer
Author
optai
Date
2024-10-22 07:41
Views
254
Model Compression Research Engineer
Key Responsibilities
Development of Model Compression Technologies:
• Neural Architecture Search (NAS)
• Quantization Aware Training (QAT) & Post Training Quantization (PTQ)
• Knowledge Distillation (KD)
Qualifications
• Master’s degree in a related field or over 2 years of relevant experience
• Experience with major deep learning frameworks such as TensorFlow and PyTorch
• Proficiency in English for communication with international colleagues
• Strong teamwork and communication skills
• Ability to conduct independent research projects
• Capability to understand and apply the latest research papers
Preferred Qualifications
• Publications in related fields (international conferences or SCI/SCIE journals)
• Experience in optimizing DL/ML on specific hardware accelerators (e.g., GPUs, TPUs, FPGAs)
• Experience with model serving frameworks for compression (e.g., TensorFlow Serving, ONNX Runtime)
Working Conditions
• Employment Type: Full-time (up to 3-month probation period with the same salary), military service exception possible
• Working Hours: Flexible hours (arrival before 11 AM & focused work from 11 AM, minimum 4 hours per day & 40 hours per week)
• Work Locations:
- LG Sciencepark E10, Superstar Lab 3, 70 Magokjungang 10-ro, Gangseo-gu, Seoul
- SBA M+ 511, 14 Magokjungang 8-ro, Gangseo-gu, Seoul
Recruitment Process
• Step-1: Document Screening
• Step-2: Technical Interview
• Step-3: Final Interview and Salary Negotiation
Key Responsibilities
Development of Model Compression Technologies:
• Neural Architecture Search (NAS)
• Quantization Aware Training (QAT) & Post Training Quantization (PTQ)
• Knowledge Distillation (KD)
Qualifications
• Master’s degree in a related field or over 2 years of relevant experience
• Experience with major deep learning frameworks such as TensorFlow and PyTorch
• Proficiency in English for communication with international colleagues
• Strong teamwork and communication skills
• Ability to conduct independent research projects
• Capability to understand and apply the latest research papers
Preferred Qualifications
• Publications in related fields (international conferences or SCI/SCIE journals)
• Experience in optimizing DL/ML on specific hardware accelerators (e.g., GPUs, TPUs, FPGAs)
• Experience with model serving frameworks for compression (e.g., TensorFlow Serving, ONNX Runtime)
Working Conditions
• Employment Type: Full-time (up to 3-month probation period with the same salary), military service exception possible
• Working Hours: Flexible hours (arrival before 11 AM & focused work from 11 AM, minimum 4 hours per day & 40 hours per week)
• Work Locations:
- LG Sciencepark E10, Superstar Lab 3, 70 Magokjungang 10-ro, Gangseo-gu, Seoul
- SBA M+ 511, 14 Magokjungang 8-ro, Gangseo-gu, Seoul
Recruitment Process
• Step-1: Document Screening
• Step-2: Technical Interview
• Step-3: Final Interview and Salary Negotiation
