At Apheris we power federated data network in life sciences to address the data bottleneck in training highly performant ML models. Publicly available molecular datasets are insufficient to train highquality ML models that meet industry requirements. Our product addresses this by hosting networks where biopharma organizations collaboratively train higher quality models on their combined data. The Apheris product is a set of drug discovery applications enriched with the proprietary data of network participants. Our federated computing infrastructure with builtin governance and privacy controls ensure that the data IP and ownership always stays with the data custodians.
As we are doubling down on ADMET (absorption distribution metabolism excretion and toxicity) use cases as a focus area within our drug discovery work we are looking for a Principal ML Engineer to lead the technical direction for our ADMET models. This is a handson highimpact role focused on advancing the state of the art in applying foundational models to drug discovery problems. Youll work closely with our leadership team and will serve as the technical authority on ML modeling architecture and experimentation in this domain. While this is not a people management role you will guide and mentor other engineers and researchers on a content level.
You should bring expertise in training and deploying different neural network architectures (graph neural networks transformers and data preparation for ADMET modelling. You should also understand the application of these models within industrial drug discovery workflows and have a track record of setting strategy breaking down complex technical problems and delivering impactful ML systems.
If you want to be part of a missiondriven team building cuttingedge AI systems for life sciences and you know what it takes to move from foundational models to domainspecific impact this role is for you.
What you will do
Drive the technicalapproachfor ML applications inADMETleveragingstate of the artML approaches like graph neural networks and transformers.
Design and implement model extensions for specific tasks including data distillation benchmarking and evaluation pipelines.
Work with ourcustomersand potentially academic partnerstodefine data preprocessingselection and benchmarking strategies for novel training tasks involvingADMETdata includingleveraging and harmonizing assay data fromdifferent sources.
Collaborate crossfunctionally to ensure models address realworld drug discovery needs.
Mentor and guide team members on a content level supporting the planning and breakdown of complexADMETmodeling projects.
Influence strategic decisions on model architecture datastrategy andexperimentation design.
Contribute to publications or opensource contributions where relevant.
What we expect from you
By month 3:Develop a deep technical understanding of theApherisproduct and how it maps to the current ADMET usecases we are working on.Take ownership of anADMETmodeling stream.Build relationships with product and engineering leadership.Develop a roadmap and experiment plan forpreparing data andadapting models to one highvalue use case.
By month 12:Lead multiple ML efforts inADMETanddemonstratemeasurable progress in model performance and realworld impact. Mentor colleagues and set strategic direction for the domain.
You should apply if
You have a PhD (or equivalent experience) in ML computational biologycomputational chemistryor cheminformaticsanda track recordof applying ML to realworld drug discovery problems.
You have deep experience building and trainingADMET machine learningmodelsbased ongraph neural networks(e.g.ChemPropandtransformer approachesusingPyTorchPyTorchLightning or similar frameworks.
You can break down and drive on ambitious modeling plans.
You understand howADMETmodels are used in the drug discovery lifecycle and can align your work to practical use cases.
Bonus points if
Youhave deep experience in ADMET data including an understanding of assay protocols and how to map protocols to each otherand can design preprocessing training and evaluation workflows.
You have experience in federated learning privacypreserving ML or secure model training.
Youvepublished in toptier ML or biology journals/conferences (e.g.NeurIPS ICML Nature Methods Bioinformatics)
Youvecontributed to opensource ML orcheminformaticstooling.
You have handson experience working withADMET assays and DMPK stakeholders
You have experience guiding technical direction in a fastpaced researchoriented environment.
Remotefirst working work where you work best whether from home or a coworking space near you
Great suite of benefitsincluding a wellbeing budget mental health benefits a workfromhome budget a coworking stipend and a learning and development budget
Regular team lunches and social events
Generous holiday allowance
Quarterly All Hands meetup at our Berlin HQor a different European location
A fundiverse team of missiondriven individuals with a drive to see AI and ML used for good
Plenty of room to grow personally and professionally and shape your own role
About Apheris
Apheris powers federated life sciences data networks addressing the critical challenge of accessing proprietary data locked in silos due to IP and privacy concerns. Publicly available datasets are insufficient to train highquality ML models that meet industry requirements. Our product addresses this by enabling life sciences organizations to collaboratively train higher quality models on complementary data from multiple parties. We are now doubling down on two key areas of interest: structural biology and ADMET.
Logistics
Our interview process is split into three phases:
Initial Screening: If your application matches our requirements we invite you to an initial video call to explore the fit. In this 3045 minutes interview you will get to know us and the role. The interviewer will be interested in your relevant experiences and skills as well as answer any question on the company and the role itself that you may have.
Deep Dive: In this phase a domain expert from our team will assess your skills and knowledge required for the role by asking you about meaningful experiences or your solutions for specific scenarios in line with the role we are staffing.
Final Interview: Finally we invite you for up to three hours of targeted sessions with our founders talking about our culture and meeting future coworkers on the ground.
Disclaimer: Drjobpro.com is only a platform that connects job seekers and employers. Applicants are advised to conduct their own independent research into the credentials of the prospective employer.We always make certain that our clients do not endorse any request for money payments, thus we advise against sharing any personal or bank-related information with any third party. If you suspect fraud or malpractice, please contact us via contact us page.