Senior ML Research Engineer
- Role
- AI / ML
- Experience
- Senior
- Employment
- Full-time
Open to DE only. Set where you work from to check your eligibility.
No BS summary
Senior ML Research Engineer with PhD/MSc and 2+ years of experience applying ML to scientific problems, specifically in molecular/protein structure modeling. Must be expert in Python and PyTorch, with deep familiarity in structural biology data formats and tooling. Experience with federated learning is a plus.
Core skills
Required skills
Optional skills
Required languages
About Apheris
At Apheris, we are building the future of how AI is applied in pharmaceutical R&D. We enable leading pharmaceutical teams to discover and develop drugs faster. We host the industry’s largest federated data networks for drug discovery AI, spanning co-folding, ADMET, and antibody developability.
Across these networks, models are trained on proprietary industry datasets to achieve higher performance and broader applicability while keeping data control and IP protected. We deliver these superior models through drug discovery applications that enable teams to run them at scale, further customize them, and integrate them into existing R&D workflows.
- AI Structural Biology (AISB) Network: Pharmaceutical companies collaborate in the field of co-folding, structure-based binding affinity predictions and antibody design.
- ADMET Network: Pharmaceutical and biotech companies collaborate to improve small-molecule property prediction and expand into further drug modalities.
- Antibody Developability Network: Pharma partners collaborate to federate historical and purpose-built antibody developability data sets for secure ML training, without data leaving each partner’s environment.
About the role
We are looking for a Senior Machine Learning Research Engineer to help drive the research and development of machine learning models for molecular and structural biology.
This is a hands-on role at the intersection of foundation models, structural biology, and federated learning. You'll execute research projects, turning ambitious scientific goals into frontier ML models that can be evaluated, released, and used in real drug-discovery workflows.
About you
What you will do
- Develop and improve ML models in molecular and structural biology, such as co-folding and binding affinity models, for drug design applications and workflows, driving them from ideation through prototyping iterations to robust tooling.
- Build effective benchmarking and evaluation strategies for model evaluation and iterate and refine existing modelling approaches based on data-driven insights.
- Diagnose and resolve data quality and pipeline issues that affect model quality.
- Stay up to date with a rapidly evolving research literature and identify best public approaches to aid in research and development.
- Collaborate with customers, partner-facing engineers, and external collaborators to support real-world drug design use cases.
What we expect from you
- You have a PhD or MSc in machine learning, computational biology, computational chemistry, bioinformatics, physics, or a related field, with at least 2 years of professional experience applying ML to scientific problems.
- You have hands-on experience training, fine-tuning and extending deep learning models for molecular or protein structure modelling.
- You are able to rigorously interrogate ML models, their training, and scientific benchmarks, and translate insights into impactful improvements.
- You are an expert in Python and PyTorch, can produce reliable and clean code, and are comfortable with multi-GPU and distributed training.
- You have deep familiarity with structural biology and protein–ligand data formats, quality metrics and tooling.
- You proactively identify opportunities to contribute scientifically in order to impact the organizational goals.
Nice to have
- You have experience in federated learning, privacy-preserving ML, or secure model training.
- You have experience developing ML models for drug design in pharmaceutical or biotech environments.
- You have published at top-tier ML or structural biology venues or have contributed to open-source projects in that space.
What we offer you
- Industry-competitive compensation, including early-stage virtual share options
- Remote-first working – work where you work best, whether from home or a co-working space near you
- Great suite of benefits, including a wellbeing budget, mental health benefits, a work-from-home budget, a co-working stipend and a learning and development budget
- Generous holiday allowance
- Office Days at our Berlin HQ or a different European location (3x a year)
- A fun, diverse team of mission-driven individuals with experience across leading organizations and a drive to see AI and ML used for good
Logistics
Our mission statement
What you'll do
- Develop and improve ML models in molecular and structural biology, such as co-folding and binding affinity models, for drug design applications and workflows, driving them from ideation through prototyping iterations to robust tooling.
- Build effective benchmarking and evaluation strategies for model evaluation and iterate and refine existing modelling approaches based on data-driven insights.
- Diagnose and resolve data quality and pipeline issues that affect model quality.
- Stay up to date with a rapidly evolving research literature and identify best public approaches to aid in research and development.
- Collaborate with customers, partner-facing engineers, and external collaborators to support real-world drug design use cases.
What they require
- PhD or MSc in machine learning, computational biology, computational chemistry, bioinformatics, physics, or a related field, with at least 2 years of professional experience applying ML to scientific problems.
- Hands-on experience training, fine-tuning and extending deep learning models for molecular or protein structure modelling.
- Able to rigorously interrogate ML models, their training, and scientific benchmarks, and translate insights into impactful improvements.
- Expert in Python and PyTorch, can produce reliable and clean code, and are comfortable with multi-GPU and distributed training.
- Deep familiarity with structural biology and protein–ligand data formats, quality metrics and tooling.
- Proactively identify opportunities to contribute scientifically in order to impact the organizational goals.
Benefits
- Industry-competitive compensation, including early-stage virtual share options
- Remote-first working – work where you work best, whether from home or a co-working space near you
- Great suite of benefits, including a wellbeing budget, mental health benefits, a work-from-home budget, a co-working stipend and a learning and development budget
- Generous holiday allowance
- Office Days at our Berlin HQ or a different European location (3x a year)
- A fun, diverse team of mission-driven individuals with experience across leading organizations and a drive to see AI and ML used for good
At Apheris, we are building the future of how AI is applied in pharmaceutical R&D. We enable leading pharmaceutical teams to discover and develop drugs faster. We host the industry’s largest federated data networks for drug discovery AI, spanning co-folding, ADMET, and antibody developability. Across these networks, models are trained on proprietary industry datasets to achieve higher performance and broader applicability while keeping data control and IP protected. We deliver these superior models through drug discovery applications that enable teams to run them at scale, further customize them, and integrate them into existing R&D workflows. AI Structural Biology (AISB) Network: Pharmaceutical companies collaborate in the field of co-folding, structure-based binding affinity predictions and antibody design.ADMET Network: Pharmaceutical and biotech companies collaborate to improve small-molecule property prediction and expand into further drug modalities.Antibody developability Network:Pharma partners collaborate to federate historical and purpose-built antibody developability data sets for secure ML training, without data leaving each partner’s environment.