Tech Lead, AI and Data Systems

GeneFab•Alameda, CA

About The Position

GeneFab is building a cell and gene therapy foundry centered on a connected AI data system. The Tech Lead, AI and Data Systems will build on the current infrastructure and architect and own the platform end to end, including its data foundation, models and agents, and GMP-qualified control and historian systems. The role sets the technical direction for how GeneFab differentiates itself from traditional CDMOs and builds the team to deliver the platform. The platform will connect data from equipment and instruments, electronic batch records, LIMS, QC results, the quality system, and tech transfer records. It will capture structured, contextualized data at the source, support machine learning and AI for operational use, and establish governance suitable for GMP. The role will also design integration pathways for future robotics and industrial automation, develop digital twins and closed-loop optimization within validated limits, and make platform capabilities valuable to clients through visibility, predictive timelines, faster tech transfer, and richer comparability data. The Tech Lead will manage technology partners and vendors, hire and mentor data and machine learning professionals, and represent the platform with clients, investors, and strategic partners. A dedicated automation engineer is expected to join later and integrate with the system designed by this role.

Requirements

  • Bachelor’s degree or higher in computer science, data science, engineering, bioengineering, or a related field.
  • 10+ years building data platforms, ML systems, or digital products, including 3+ years leading technical teams or programs.
  • Substantial experience in life sciences, biopharma manufacturing, or another regulated industry.
  • Demonstrated ability to architect data infrastructure end to end, including ingestion, storage, modeling, and governance, and take ML or AI work from prototype to production.
  • Strong Python and SQL skills, with fluency in modern data and ML tooling such as cloud data platforms, pipelines and orchestration, experimentation, and model monitoring.
  • Hands-on experience applying modern AI, including LLMs and agentic workflows, to operational problems.
  • Working knowledge of cGMP, data integrity, CSV or GAMP 5, and 21 CFR Part 11, or ability to learn them quickly and incorporate them into the architecture.
  • Experience selecting and managing technology vendors and partners.
  • Clear communication skills and ability to explain tradeoffs to scientists, quality leaders, and executives.

Nice To Haves

  • MS or PhD in computer science, machine learning, computational biology, or a related field.
  • Cell or gene therapy manufacturing experience; autologous, allogeneic, or iPSC-derived products are a plus.
  • Experience with bioprocess data, including process analytics, multivariate modeling, digital twins, or Bayesian optimization.
  • Familiarity with MES, electronic batch records, historians, LIMS integration, and standards such as ISA-88 and ISA-95.
  • Exposure to lab or process automation and robotics, such as Biosero Green Button Go or Tecan Fluent, as an integration target rather than a core requirement.
  • Experience validating control systems and monitoring AI or machine learning models in regulated operations.
  • Startup or CDMO experience, including customer-facing technical work.
  • Open-source work, publications, or products demonstrating a record of building in the open and advancing the field.

Responsibilities

  • Architect and build a unified, governed, traceable data platform connecting equipment and instrument data, electronic batch records, LIMS, QC results, the quality system, and tech transfer records, extending the current Veeva, LabKey, and LIMS stack.
  • Capture process, material, environmental, and analytical data in structured, contextualized form at the source so each run can become training data and deviations can provide signals.
  • Deliver ML and AI capabilities for process modeling and DoE, yield and deviation prediction, anomaly detection, automated batch record review, and LLM-based agents for tech transfer, investigations, and knowledge reuse, with human oversight and documented change control.
  • Build toward process digital twins and closed-loop optimization, with models recommending and eventually adjusting process parameters across platforms such as G-Rex, WAVE, and PBS Vertical Wheel within validated limits.
  • Establish standards for data integrity, lineage, model validation, monitoring, and drift control in GMP, including relevant CSV, GAMP 5, 21 CFR Part 11, and cybersecurity practices, in partnership with Quality and regulators.
  • Define the integration layer, data contracts, and APIs to support future robotics, liquid handlers, and automated unit operations; scope the future automation engineer role and guide technology selections.
  • Productize the platform for clients, including real-time batch visibility, predictive timelines, faster tech transfer, and richer comparability data.
  • Evaluate and manage AI, data, and cloud partners, including pilot design, success criteria, data rights, and IP terms.
  • Hire and mentor data engineers, ML engineers, and data scientists; establish expectations for code, documentation, testing, and engineering culture.
  • Represent the platform with clients, investors, and strategic partners, and communicate GeneFab’s technical differentiation.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service