[Mogam Biotechnology Research Institute] Hiring for Small Molecule AI New Drug Development Researcher (PhD, Entry-level·Experienced)
(재)목암생명과학연구소 · 서울 서초구 강남대로41길 15-19
✨Job Description - Small Molecule AI Drug Discovery Researcher - Develop and apply AI/ML models for small-molecule drug discovery to derive hit/lead candidates that can be validated experimentally - Develop methodologies at a level suitable for publication in academic papers - Develop predictive models for activity, ADMET, and toxicity - Develop generative models and structure-based molecular design, and perform multi-objective optimization - Conduct virtual screening, active learning, and training-data curation - Reproduce and improve the latest models, and publish in SCI journals and AI conferences - Interpret results and share candidates with the chemical biology research team ✅Qualifications - PhD holder or expected to obtain the degree before joining - PhD in computer science·AI, computational chemistry, chemoinformatics, pharmacy, chemistry, or related fields - 0–5 years of experience after obtaining a PhD (including postdoctoral experience) - Doctoral-level research experience in AI drug discovery - At least one representative first-author paper in a related field - Strong ability to develop models proficiently with Python and PyTorch or JAX - Ability to reproduce and validate papers and open-source models - Basic medicinal chemistry knowledge (SAR, ADMET) and proficiency with RDKit - No disqualifying reasons under the research institute’s employment rules - No disqualifying reasons for overseas travel and work 💖Preferred - Publication experience in NeurIPS, ICML, ICLR - Experience with generative models such as diffusion, equivariant GNNs, and co-folding models - Experience with active learning, Bayesian optimization, and large-scale virtual screening - Experience participating in actual drug discovery projects or contributing to open source/conferences - Experience with docking, FEP, and MD - Preprints or publicly released models/code - Experience evaluating predictive uncertainty (calibration, applicability domain) - Employment-protected candidates (veterans, persons with disabilities, etc.) 🏠Workplace - 3rd Floor, M11 Building, 15-19, Gangnam-daero 41-gil, Seocho-gu, Seoul - Near Yangjae Station ⚡️Recruitment Process - Document screening → Personality test (online) → 1st interview (presentation interview) → 2nd interview → Compensation discussion - In the 1st interview, present your main research for about 20 minutes, followed by Q&A and technical questions - Submitted public code will also be reviewed - For experienced candidates, compensation will be discussed after reference checks, and final selection will follow a pre-employment medical examination - All results will be notified by E-mail and SMS, regardless of acceptance or rejection 👉Application Period / Method - Application period: open until filled - How to apply: apply through the recruitment website 📋Other - This is a full-time position with a 2-month probation period after joining - Office-based work 5 days a week, with flexible working hours based on 08:30~17:30 - Simultaneous applications to other openings at Mokam Life Science Research Institute and its affiliates are not allowed - Position level and compensation will be negotiated based on experience and achievements - Cloud and GPU resources provided - Papers and conference presentations are encouraged - Recruitment documents may be requested back and will be destroyed after the retention period expires
Working Conditions
- Work Period
- Long term
- Work Time
- 08:30 ~ 17:30
Recruitment Conditions
- Application Deadline
- Deadline for hiring
- Employment type
- Full-time job
- Salary
- A decision after an interview
Qualifications
- Experienced
- No Experience Required
- Education
- Master’s or higher
- Preferred Conditions
- Experience with NeurIPS, ICML, and ICLR papers Experience with generative models such as diffusion, equivariant GNNs, and co-folding models Experience with active learning, Bayesian optimization, and large-scale virtual screening Experience participating in real drug discovery projects or contributing to open source / academic conferences Experience with docking, FEP, and MD Has preprints or publicly released models/code Experience evaluating predictive uncertainty (calibration, applicability domain) Employment-protected category (veterans, people with disabilities, etc.)
- Benefits & Welfare
- Cloud·GPU resource support Encouragement for paper·conference presentations