Bioinformatics Data Engineer Rivercell
Data generation infrastructure for AI Virtual Cell models in drug discovery.
Permanent
Paris
A few days home
Salary: Not specified
Skills we're looking for
Motivational skills
Pytorch
AWS
Python
You'll be part of
Artificial Intelligence / Machine Learning
Pharmaceutical / Biotech
Rivercell’s mission is to change how medicines are discovered by teaching AI to understand the human cell. Developing a single drug still takes years with an 90% failure rate in human. Predicting how cells respond to treatment before going to the lab would make it faster, and open up possibilities that are out of reach today.
That’s the promise of AI Virtual Cells: world models that learn the underlying rules of how cells respond to drugs and genetic changes, much as AlphaFold learned to predict protein structure. What holds them back is data. The vast, diverse, multimodal and time-resolved perturbational data they need doesn’t exist at scale, so we are building the infrastructure that generates it.
Our platform applies chemical and genetic perturbations to large cell populations and reads out their molecular and morphological responses at single-cell resolution, across millions of perturbation and context combinations. We then use that data to train our own world model of the cell.
Doing this takes a truly multidisciplinary team, where experts in thin films, microfluidics and instrumentation work side by side with experts in machine learning, computational biology and cell biology.
You'll be working on
The Role
You will join Rivercell's team as a Bioinformatics Data Engineer, contributing to the datasets used to train and evaluate our AI virtual cell models. You will develop and maintain pipelines that turn sequencing and imaging data into versioned, analysis-ready datasets. Working with our ML scientists, biologists, chemists, and engineers, you will help improve data quality, harmonization, and reproducibility.
The Challenge
We believe the AI virtual cell, a world model that can predict how cells will respond before an experiment runs, is the biology challenge of our times. Rivercell's cell-on-a-chip technology offers the opportunity to develop models alongside the platform generating their training data. You will work with our biology and engineering teams to explore which experiments, data, and architectures make those predictions more reliable. Our goal is to make biological research faster and more predictive, with models that help researchers decide what to test next.
Build our omics pipelines, starting with single-cell, from FASTQ to analysis-ready matrices: alignment and quantification, CRISPR guide assignment, cell calling, ambient RNA and doublet handling, and per-run quality control
Build the imaging pipelines for live-cell brightfield and fluorescence time-lapse data: illumination correction, segmentation, tracking, and feature and embedding extraction
Internalize and harmonize relevant publicly available datasets with Rivercell's own data
Set up dataset versioning, lineage, and release management, so that every dataset behind a model, a paper, or a benchmark can be traced to its raw data and pipeline version and every experiment is reproducible
Build the tooling that generates and audits contamination-controlled train/test splits for our benchmarks
Run the data infrastructure: cloud storage and compute for tens of terabytes, cost control, and data loading fast enough to keep GPUs busy
Build the data side of our closed lab-in-a-loop, in which models propose experiments, the lab runs them, and the results return as retraining-ready data
Opportunity to work on a cutting-edge project in the field of biotech
Opportunity to join an ambitious team and impactful startup among the first employees
Competitive salary and equity package
Exciting opportunities for personal and professional growth within the team
We're looking for
You have an MSc or PhD in bioinformatics, computational biology, computer science, or a related field
You have 3+ years of experience building and running bioinformatics pipelines in production, in industry, a core facility, or a large consortium
You have processed single-cell RNA-seq data from raw reads (Cell Ranger, STARsolo, kallisto/bustools, alevin-fry, or equivalent) and work comfortably in the AnnData / scverse ecosystem
You write strong Python and apply sound engineering practice: workflow managers, containers, tests, CI, and documentation
You have experience with data versioning on large datasets, with harmonizing heterogeneous datasets, and with cloud (AWS or GCP) or HPC infrastructure
You have experience with image processing at scale, ideally microscopy: segmentation, tracking, and feature or embedding extraction (Cellpose, StarDist, CellProfiler, or deep-learning models)
You have experience with high-performance data management for model training: array and columnar formats (Zarr, TileDB-SOMA, Parquet, OME-Zarr), sharding and streaming from object storage, and PyTorch data loaders that keep GPUs busy
An autonomous, committed, enthusiastic, fun to work with person with a "can-do", creative, and challenging mindset
You have excellent communication skills and are fluent in English. Professional proficiency in French is helpful but not required.
Please let us know in your application if you specifically have experience with one or several of the following items:
Pooled CRISPR screen or Perturb-seq data, including guide calling
Multimodal single-cell data and cross-modality cell matching
Sample tracking or LIMS integration, and daily work alongside a wet lab
Open-source bioinformatics contributions (nf-core, scverse) or public dataset releases (GEO, CELLxGENE, Hugging Face)
How we hire
Throughout the recruiting process, you will meet 4 to 6 team members of Rivercell.
Introductory call (up to 30mn, videocall)
Technical interview (up to 90mn)
Performance interview (up to 90mn, in person)
Culture interview (up to 60mn, in person)