Data Scientist; Clinical Data)

Bioptimus is building the first universal AI foundation model for biology to fuel breakthrough discoveries and accelerate innovation in biomedicine. With more than $75M in funding, Bioptimus is a fast-growing start-up headquartered in Paris, incorporated in October 2023. Backed by leading international venture capitalists, our world-class team of scientists and engineers is redefining the frontiers of AI and life sciences.

Data Scientist (Clinical Data)

Bioptimus’ mission is to accelerate biomedical innovation by building the reference foundation model of biology that will unlock AI superpowers for the biomedical ecosystem. As a well-funded and fast-growing start-up headquartered in Paris and incorporated in October 2023, we are growing a world-class team of scientists, engineers, and product leaders.

This is a remote role. We’re headquartered in Paris, but the position can be performed remotely outside of Paris.

We are looking for a technical, execution-focused Senior Data Scientist (Clinical Data) to bridge the gap between unstructured, real-world data, and our frontier AI models. In this role, you will be the authority on clinical data structures, serving as the technical link during conversations with our global partners to standardise and harmonise data pipelines.

Operating within our STELA program, you will structure our clinical datasets. You are a hands-on technical expert who writes reproducible code, enforces incoming data QC, and designs the data dictionaries and ontologies for our models.

We recently launched the Spatial Tissue Embedding Learning Atlas (STELA)—a multinational spatial data generation initiative anchored by strategic partnerships with 10x Genomics and Broad Clinical Labs. STELA serves as the data backbone for M-Optimus, aiming to profile up to 100,000 patient specimens across three continents (US, Europe, and Asia). This will integrate high-resolution spatial transcriptomics, histopathology imaging, and longitudinal clinical records to bring forward the next era of biological AI and precision medicine.

• Partner Data Engineering & Collaboration
  • Technical Partner Interface:
    Participate directly in technical conversations with external partners (hospitals, research institutions, CROs/CMOs). Dive into the details of diverse clinical data structures to understand how data is captured, stored, and extracted.
  • Order from Uncertainty:
    Translate ambiguous source data into harmonized, AI-ready assets.
  • Ontology Integration:
    Map and align diverse clinical data to industry-standard biomedical ontologies (e.g., SNOMED, ICD, etc…) with an emphasis on clinical oncology and immunology data.
• Data Governance, Quality, and Automation
  • Data Dictionary Architecture:
    Design, build, and maintain data dictionaries, schemas, and metadata models that align with STELA’s multimodal pipeline requirements, while ensuring integration with existing pipelines.
  • Enforcing Ingest Quality:
    Establish, automate, and enforce data quality control (QC) and validation frameworks to check incoming partner data for integrity, completeness, and programmatic consistency.
  • Reproducible Pipeline Code:
    Write production-grade Python code to automate data cleaning and harmonization tasks.
• Clinical Reality & Intuition
  • Clinical Reality:
    Practical understanding of how clinical data is generated in the real world (hospitals, trials, CROs). You understand the gaps between ideal protocols and messy clinical realities, and you know what red flags to look for in incoming data.
  • The Investigative Mindset:
    You know what questions to ask partners to get to the "ground truth" of their data structures. Actively audit data to find missing variables, anomalies, and hidden biases.
  • Oncology…