Sr. Scientist, Generative Protein Design

Merck Merck · Pharma · MA

Seeking an AI/ML protein engineer to apply structure-based generative AI and machine learning for de novo therapeutic protein design and optimization, integrating computational methods with structural biology and experimental screening data. The role involves training ML models, processing experimental data, and evaluating/improving design strategies.

What you'd actually do

  1. Create de novo therapeutic proteins using structure-guided generative AI and machine learning-based protein design and engineering technologies.
  2. Integrate AI/ML protein design methods with structural biology and high-throughput experimental screening data to devise and execute de novo protein design and optimization strategies.
  3. Process and analyze experimental functional data in context of protein structure, and optimize workflows using data for hit-to-lead optimization.
  4. Evaluate and improve computational protein design strategies, methods and models (zero- and few-shot).
  5. Train ML models to integrate structural data with experimental datasets to advance therapeutic programs.

Skills

Required

  • Structure-based generative AI methods for protein design and engineering
  • de novo design
  • lead optimization
  • in silico prediction
  • RFdiffusion
  • Boltzgen
  • BindCraft
  • ProteinMPNN
  • AlphaFold
  • applying experimental data
  • affinity
  • stability
  • solubility
  • optimize protein sequence/structure/function
  • data analysis
  • visualization
  • Biopharmaceutical Industry
  • Biopharmaceuticals
  • Biopharmaceutics
  • Data Engineering
  • Design Applications
  • Drug Discovery Process
  • Generative AI
  • Inclusive Leadership
  • Inclusive Practices
  • Machine Learning (ML)
  • Protein Design
  • Protein Engineering
  • Structural Biology
  • Systematic Problem Solving
  • Testing
  • Therapeutic Proteins
  • Workflow Optimization

Nice to have

  • protein structure and sequence representations
  • featurization
  • embeddings
  • computational protein design method/algorithm development
  • training/validating data-driven ML models

What the JD emphasized

  • structure-based generative AI methods for protein design and engineering
  • experimental data to optimize protein sequences for function
  • Proven industry track record of success working with cross-functional teams
  • high-impact publications

Other signals

  • Generative AI for protein design
  • Structure-based computational protein design
  • Integrate AI/ML with experimental data