프리퍼드네트웍스에서 Drug Discovery 분야의 혁신적인 알고리즘을 연구하고 개발할 리서처를 모집합니다. 분자 동역학, Neural Network Potential, 또는 단백질 구조 예측 중 하나 이상의 전문 지식이 필수입니다. Python을 활용한 복잡한 알고리즘 구현 능력과 Linux 환경에서의 고성능 컴퓨팅 경험이 필요합니다. 최첨단 계산 과학을 통해 신약 개발 플랫폼을 구축하는 도전적인 업무를 수행하게 됩니다.
Preferred Networks（PFN）のDrug Discovery領域を担うリサーチャーを募集します。
創薬分野における計算科学の発展はめざましく、創薬標的となる生体内高分子の同定からその構造・機能の予測、あるいは医薬品候補分子の設計・探索・最適化（薬理活性・毒性・動態予測）などの分野において応用が進んでいます。
PFNのDrug Discoveryチームでは、結合自由エネルギー計算サービスP-FEPをはじめとする最先端技術と創薬分野におけるドメイン知識を高度に融合したサービスを製薬企業に提供しています。現在はこれらの実績ある技術基盤をさらに拡張し、創薬プロセスのより広範な工程を一貫してカバーする包括的な創薬プラットフォームの構築を目指しています。
当チームでは、創薬現場の課題を解決しうる新規技術開発を担うメンバーを募集しています。PFNが掲げるミッション・バリュー[https://tech.preferred.jp/ja/blog/2025-mission-values/\](https://tech.preferred.jp/ja/blog/2025-mission-values/) に共感し、最先端の理論を自らの手で実装し「現実世界を計算可能にする」卓越した技術力と、自らコトをおこす（Be Proactive）情熱を兼ね備えたプロフェッショナルを求めています。
チームミッション
業務内容
参考
We are hiring a Researcher to drive Preferred Networks (PFN)’s Drug Discovery initiatives.
The advancements of computational science in drug discovery have been remarkable, and its applications are expanding across fields ranging from the identification of biomolecular drug targets and the prediction of their structures and functions to the design, exploration, and optimization of drug candidate molecules (including predictions for pharmacological activity, toxicity, and pharmacokinetics).
The PFN Drug Discovery team provides pharmaceutical companies with solutions, such as the binding free energy calculation service P-FEP, that integrate advanced computational methodologies with deep domain expertise. We are currently building on these core technologies to create a comprehensive "Drug Discovery Platform" – an end-to-end solution aimed to accelerate a wider range of processes in the drug discovery workflow.
We are recruiting a researcher to lead the research and development of novel technologies that address critical challenges in drug discovery. We seek a professional who deeply resonates with our Mission and Values [(https://tech.preferred.jp/ja/blog/2025-mission-values/) ](https://tech.preferred.jp/ja/blog/2025-mission-values/)and possesses the exceptional engineering capability to implement cutting-edge theory into robust software.
Team Mission
Responsibilities
Additional Information
Drug Discovery領域における専門知識（下記の内、いずれか1つ以上に関する深い知識や経験）
分子動力学シミュレーション（FEPなどの高精度な活性予測技術）
Neural Network Potential (NNP) / Machine Learning Interatomic Potential (MLIP)
Protein folding / Structure-aware prediction
ソフトウェア開発
Python等を用い、複雑なアルゴリズムや理論を自力で実装できる能力
コンピューターアーキテクチャを理解し、ソフトウェアの実行効率や、計算量を意識したプログラムを実装できる能力
Unix/Linux環境における計算リソース（GPU/大規模クラスタ等）の使用・制御経験
Expertise and deep experience in at least one of the following areas:
Molecular dynamics simulation (e.g., high-accuracy affinity prediction technologies such as Free energy perturbation)
Neural Network Potential (NNP) / Machine Learning Interatomic Potential (MLIP)
Protein folding or Structure-aware prediction
Software development skills:
Ability to independently design and implement complex algorithms and theories using Python
Ability to implement efficient programs with an awareness of computer architecture and computational complexity
Experience utilizing high-performance computing resources in a Unix/Linux environment.
業績リスト （もしあれば）
List of publications (if available)
経験、業績、能力、貢献に応じて、当社規定により優遇
Experience, performance, skills, contribution are taken into consideration.
東京都千代田区大手町１−６−１ 大手町ビル / Otemachi Bldg., 1-6-1 Otemachi, Chiyoda-ku, Tokyo, Japan 100-0004
リモート勤務制度あり （日本国内に限る) / Remote work system available (limited to work in Japan)
