Bioinformatics Engineer, Pipelines

About the role

We are looking for a Lead Bioinformatics Pipeline Engineer to build and scale Mithrl’s multi-modal scientific processing pipelines. You will own the workflows that transform raw biological data into clean, reproducible outputs that power Mithrl’s AI Co-Scientist.

Responsibilities

• Design and maintain production-grade bioinformatics pipelines for a wide range of data modalities, including microarray, cell painting, WGS and WES, spatial transcriptomics, flow cytometry, ATAC-seq, and methyl-seq
• Build workflows using Nextflow, nf-core modules, or similar engines with a focus on reproducibility, validation, and scalability
• Implement quality control, validation, and provenance tracking for all supported modalities
• Collaborate with the Tabular Data Team to ensure pipeline outputs map cleanly into Mithrl’s internal schemas, including variable ID coercions, metadata normalization, and feature name harmonization
• Work with the Knowledge Curation Team to align outputs with reference genomes, annotations, and biological ontologies
• Produce structured output artifacts so users can download processed data and supporting metadata directly through the platform

Requirements

• 6 to 8 years of experience in bioinformatics workflow engineering or computational biology
• Strong experience with Nextflow, nf-core, WDL, CWL, Snakemake, or similar workflow systems
• Proficiency in Python or R for data processing, QC, and pipeline logic
• Hands-on experience building pipelines for multiple biological data types, including genomics, single cell, imaging, flow cytometry, spatial data, or epigenomics
• Strong understanding of secondary and tertiary data layers and how they integrate with downstream analysis systems
• Experience integrating pipeline outputs with data stores, schemas, or ML-ready formats

Qualifications

• Nice to have: Experience executing pipelines in cloud environments such as AWS Batch, ECS, Tower, or Nextflow Cloud
• Nice to have: Experience with imaging workflows such as CellProfiler, DeepCell, or Squidpy
• Nice to have: Familiarity with genomic reference databases, annotation formats, and biological ontologies
• Nice to have: Previous work in a tech bio startup, biotech R&D group, or scientific software company