Scientific Technical Lead, Early Stage PDST CMC
$109,500–$208,500 year
HybridNorth Chicago, Illinois, United States
Job Summary
Develop, validate, and deploy predictive models supporting early-stage biologics process development, including upstream performance, downstream purification, and critical quality attribute outcomes. Design hybrid modeling approaches combining first-principles understanding with data-driven techniques to enable digital twin concepts and in-silico optimization. Partner with scientists to define data strategies, address quality challenges, and ensure all analytical work adheres to GxP principles and regulatory expectations. Architect intelligent workflows utilizing machine learning, retrieval-augmented generation, or orchestration pipelines to automate and accelerate experimental design, DoE, and Bayesian optimization strategies. Collaborate with cross-functional teams to translate complex analyses into actionable insights for regulatory submissions, technology transfer, and manufacturing decisions.
Required Qualifications
- Bachelor's degree in computer science or a related discipline with 7 years' experience
- Master's Degree with 6 years' experience
- PhD with 2 years' experience in IT, application program development
- Respective years of hands-on experience building and deploying data science or machine learning solutions in a scientific or engineering-intensive environment
- Expert-level Python proficiency
- Deep familiarity with the scientific Python ecosystem (NumPy, pandas, scikit-learn, PyTorch or TensorFlow)
- Modern data engineering (cloud, big data, pipeline orchestration)
- Strong foundation in business analytics
- Mastery of tools such as R, Dataiku, AWS SageMaker, Spark, Tableau
- Experience with design of experiments (DoE) methodologies
- Bayesian methods
- Active learning in scientific applications
- Familiarity with knowledge graph, retrieval-augmented, or orchestrated AI/LLM-based systems applied to scientific or technical domains
- Experience applying data science in a GxP-regulated environment
- Working knowledge of FDA/EMA expectations for process validation, continued process verification (CPV), and control strategy
- Familiarity with MLOps principles
- Model lifecycle management
- Deployment of analytical tools in regulated or enterprise environments
- Ownership orientation: you define your own problem space, drive solutions to completion, and hold yourself accountable to outcomes — not just outputs
- Solution-architect instinct: you think before you build, consider the full landscape of available approaches, and choose tools based on fit-for-purpose reasoning rather than familiarity or trend
- Scientific integrity: you build models you can explain, defend, and improve — and you apply the same standard to the work of others
- Influence through credibility: you earn the confidence of scientists, engineers, and quality professionals by being right, being clear, and being useful — not by title or volume
- Bias for impact: you are drawn to problems where the stakes are high and the analytical opportunity is real, and you are energized rather than intimidated by ambiguity
Desired Qualifications
- Advanced degree (M.S. or Ph.D.) in Data Science, Biostatistics, Chemical or Biochemical Engineering, Computational Biology, or a closely related quantitative discipline
- 5+ years of hands-on experience building and deploying data science or machine learning solutions in a scientific or engineering-intensive environment
- Experience in working with data from diverse lab and manufacturing systems (LIMS, MES, DeltaV/historian, eBR platforms)
- Building scalable data pipelines for process analytics
- Direct experience in biologics or bioprocess development (e.g., cell culture, fermentation, chromatography, filtration, or formulation) either in an industrial or academic research setting
- Familiarity with CMC development concepts, including process characterization, scale-up, technology transfer, or regulatory filing support (BLA/IND)
- Familiarity with biopharmaceutical data types including bioreactor process data, chromatography profiles, analytical assay results, and spectroscopic measurements
- Familiarity with technology transfer workflows, process characterization study design, or commercial process validation (PPQ/PV) in a biologics or pharmaceutical context
- Track record of scientific communication — publications, regulatory submissions, technical reports, or equivalent — that demonstrates the ability to convey complex analytical work clearly and credibly
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.