Principal ML Scientist – Predictive Toxicology

Stack

Responsibilities

• ▹Own the expansion into predictive toxicology and quantitative biology beyond ADME (e.g., multi-omics, image-based screening, high-throughput screening and compound-triage cascades)
• ▹Set the scientific strategy: define how in silico toxicology and quantitative biology workflows come together across the networks and which endpoints, assays and modelling approaches deliver value in drug-discovery decisions
• ▹Decide how best to use relevant data to extract the most scientific and commercial value
• ▹Span multiple scientific surfaces, from structure-based off-target liability to pathway-level mechanistic interpretation and in vivo pharmacokinetics, and integrate these workflows into the platform
• ▹Apply federated learning across partner data to deliver models no single organisation could achieve, and work with industrial partners to embed them in drug-discovery pipelines
• ▹Lead the scientific conversation with customers and partners, owning scope, evaluation, delivery and adoption in live drug programmes while shaping the roadmap around genuine need

Requirements

• ▹Strong deep learning foundations for molecular AI, e.g., graph neural networks, message-passing and transformer-based models
• ▹A profile demonstrating understanding of the concerns driving toxicity assessment in drug discovery, across any toxicity endpoints (e.g., DILI, cytotoxicity, micronucleus/genotoxicity imaging readouts)
• ▹Tangible experience building predictive models and driving adoption of toxicity models in real drug-discovery programmes or industrial R&D pipelines
• ▹Working knowledge of how RNA-seq, toxicity screens and image-based screens are used in pharma as part of routine HTS and compound triage
• ▹Scientific leadership: able to set vision, own a scientific agenda and lead technical and customer conversations independently
• ▹Comfortable staying hands-on in the modelling while setting direction and mentoring others; a scientific leadership role first, with the opportunity to build a team over time
• ▹PhD or equivalent experience in a relevant field (computational biology, cheminformatics, toxicology, ML or similar), plus 6+ years applying ML to drug discovery/life science problems

Nice to have

• ▹Experience with federated learning, privacy-preserving ML or other multi-party training environments
• ▹Evidence of prospectively validating predictive toxicity models and using them to influence compound design, prioritisation or progression decisions
• ▹Production-grade model delivery in regulated, enterprise, pharmaceutical or biotech settings, and/or a publication record in computational biology, toxicology or ML
• ▹Multi-omics and high-content imaging experience (e.g., cell painting)
• ▹Familiarity with public toxicology and bioactivity data resources (e.g., Tox21, ToxCast, LINCS/L1000) and mechanistic frameworks such as adverse outcome pathways

Soft skills

What we offer

• ▹Industry-competitive compensation, including early-stage virtual share options
• ▹Remote-first working
• ▹Wellbeing budget, mental health support, work-from-home budget, co-working stipend and learning budget
• ▹Generous holiday allowance
• ▹Office days at the Berlin HQ or another European location (3 times a year)
• ▹A high-calibre, execution-focused team with experience from leading organizations

About the company

Apheris powers federated data networks in life sciences, where biopharma organisations collaboratively train higher-quality machine learning models on their combined proprietary datasets without sharing the underlying data. Its federated computing infrastructure, with built-in governance and privacy controls, ensures data IP and ownership remain with the data custodians.