Principal Scientist I, EDDC

A*STAR RESEARCH ENTITIES; Singapore; On-site; SGD 260,000 - 360,000; Full time

Job summary

A*STAR RESEARCH ENTITIES is seeking a hands-on scientific leader to build and lead the Computational Drug Discovery function, developing an integrated platform spanning target identification to candidate selection. The role sits at the intersection of computational chemistry, structural biology, bioinformatics, physics-based modeling, and AI/ML for small-molecule discovery.

You will lead a multidisciplinary team, integrate diverse datasets, and drive strategy across hit discovery, lead

Qualifications

• PhD in a related field with 10+ years industry leadership experience.
• Strong expertise in structural biology, physics-based modeling and AI/ML.
• Proven ability to build AI-enabled workflows influencing discovery decisions.

Responsibilities

• Define and execute computational drug discovery strategy across small molecules.
• Build AI-enabled workflows for hit discovery, lead optimization, and DMPK prediction.
• Integrate datasets to inform target selection and mechanism of action.
• Lead modeling of ternary complexes and degradation efficiency.
• Apply MD, FEP, docking, QM/MM with AI/ML methods.

Skills

Python

RDKit

Molecular modeling

AI/ML methods

Leadership

Cross-functional communication

Education

PhD in relevant field

Tools

Schrödinger

OpenEye

Job description

Position Overview:

AI-driven drug discovery is a strategic priority for our organization. We are seeking a hands-on scientific leader to build and lead our Computational Drug Discovery function, creating an integrated computational platform that supports decisions from target identification and hit discovery through lead optimization, DMPK, and candidate selection.
The role sits at the intersection of computational chemistry, structural biology, bioinformatics, physics-based modeling, and AI/ML, with a focus on small molecule discovery, induced proximity, and targeted protein degradation.
The successful candidate will combine molecular modeling, structure prediction, omics and functional data analysis, machine learning, and generative AI to guide target selection, molecule design, mechanism elucidation, and therapeutic strategy in close partnership with multidisciplinary project teams.

Key Responsibilities:

• Define and execute computational drug discovery strategy across small molecule programs, integrating computational chemistry, bioinformatics, and AI from target identification to candidate selection.
• Build AI-enabled workflows for hit discovery, hit-to-lead, lead optimization, DMPK prediction, and design-make-test-analyze cycles.
• Integrate molecular, structural, omics, functional screening, and clinical datasets to inform target selection, patient stratification, mechanism of action, and therapeutic opportunity assessment.
• Lead modeling of ternary complexes, cooperativity, and degradation efficiency using structural, biophysical, and computational data.
• Apply physics-based methods such as MD, FEP, enhanced sampling, docking, and QM/MM alongside AI/ML methods including structure prediction, generative chemistry, predictive modeling, and ML-based scoring.
• Build and mentor a multidisciplinary team of computational chemists, modelers, and data scientists.
• Partner closely with chemistry, biology, structural biology, and DMPK teams to generate actionable insights and advance programs.
• Evaluate emerging technologies and represent the function in project teams, portfolio reviews, external collaborations, publications, and resource planning.

The Requirement:

• Ph.D. in Computational Chemistry, Biophysics, Structural Biology, Chemistry, Bioinformatics, Computational Biology, or related field.
  10+ years of industry experience, including scientific leadership and team building.
• Strong expertise in structural biology, physics-based modeling, molecular design, and modern AI/ML methods.
• Proven ability to build AI-enabled workflows that influence discovery decisions at program, portfolio, or organizational level.
• Experience integrating omics, functional, or translational datasets into target identification, mechanism studies, biomarker discovery, or patient stratification.
• Knowledge of targeted protein degradation, including ternary complex modeling, cooperativity, E3 ligase biology, and PROTAC or molecular glue SAR.
• Proficiency in scientific programming and data analysis, including Python, RDKit, and molecular modeling platforms such as Schrödinger, OpenEye, or equivalents.
• Strong publication record or demonstrated impact on drug discovery programs, with excellent cross-functional communication skills.

Preferred Qualifications:

• Experience advancing degrader or targeted protein degradation programs from hit identification to candidate selection.
• Experience scaling computational capabilities and driving adoption of AI/ML tools and platforms.s and platforms.