Description
Key Responsibilities
- Design and implement computational workflows for chemical, biological, and multi-omics data analysis.
- Apply cheminformatics techniques (virtual screening, molecular docking, QSAR, ADMET modeling) to support lead identification and optimization.
- Analyze next-generation sequencing (NGS), RNA-seq, proteomics, and single-cell datasets to identify biomarkers, pathways, and novel targets.
- Integrate chemical libraries with biological and clinical datasets for cross-domain insights.
- Understanding of protein-protein interaction, ADC and PDC development.
- Develop and apply machine learning/AI models for predictive drug discovery and biomarker discovery.
- Collaborate closely with medicinal chemists, molecular biologists, pharmacologists, and data scientists.
- Present findings through reports, visualizations, and presentations to internal and external stakeholders.
- DbMS

Skills:
- Strong knowledge of drug discovery, molecular biology, and systems biology.
- Proficiency in cheminformatics software (e.g., RDKit, Schrödinger, MOE, KNIME,



Pipeline Pilot).
- Hands-on experience with bioinformatics platforms and tools (Bioconductor, GATK, Galaxy, Cell Ranger).
- Solid programming skills (Python, R, SQL, Bash); experience with ML/AI frameworks (TensorFlow, PyTorch, Scikit-learn).
- Familiarity with databases such as PubChem, ChEMBL, PDB, Ensembl, UniProt, and TCGA.
- Knowledge of DBMS (e.g., MySQL, PostgreSQL, MongoDB) for managing and querying large-scale biological and chemical datasets.
- Experience with HPC or cloud computing environments (AWS, GCP, or equivalent).
- Excellent communication skills and ability to work in cross-functional teams.

Note: The interview process will include a presentation, where candidates must demonstrate an AI/ML model for drug discovery from their past experience.

Qualifications
Ph.D. or M. Pharm, M.Sc. in Cheminformatics, Bioinformatics, Computational Chemistry, Computational Biology, or a related fi

📌 Asst Manager (Ahmedabad)
🏢 Amneal
📍 Ahmedabad