Senior Machine Learning Engineer at Xing
Berlin, Berlin, Germany -
Full Time


Start Date

Immediate

Expiry Date

01 Jan, 27

Salary

90000.0

Posted On

03 Oct, 26

Experience

20 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Yes

Skills

Industry

Information Technology & Services

Description

About the job


Federated Drug Discovery AI | Remote-First | €95-115k | Germany

AI Futures has been engaged by the founding team of one of Europe's most technically ambitious drug discovery AI companies to hire a Senior ML Research Engineer. This is a hands-on research engineering role with direct impact on models used in live pharmaceutical workflows.

The company

A venture-backed AI company has built the infrastructure for collaborative machine learning across proprietary pharmaceutical datasets - without any data ever leaving its source. Their federated networks span co-folding, ADMET prediction, and antibody developability, enabling leading pharma teams to train on combined industry datasets while retaining full data control and IP protection.

They are not building demos. Their models run inside real drug discovery pipelines at some of the world's largest pharmaceutical organisations.

The role

As a Senior ML Research Engineer you will drive the development of ML models for molecular and structural biology - from ambitious scientific goal through prototyping iterations to robust tooling used in production drug design workflows.

This is research engineering in a federated environment. You build the model, you build the evaluation that proves it generalises across partner datasets you cannot see in full, and you own the benchmarking when a pharmaceutical partner asks why a binding affinity prediction moved. The hard part is not the architecture. It is making models that transfer across organisations with structurally different data, without centralising any of it.

What you'll do

  • Develop and improve ML models for co-folding, binding affinity prediction, and ADMET modelling.
  • Design rigorous benchmarking and evaluation strategies; define what "good enough" means for a drug design claim and prove it holds across federated partner datasets
  • Diagnose and resolve data quality and pipeline issues that affect model performance across heterogeneous molecular datasets
  • Track the research literature actively and identify state-of-the-art approaches relevant to live projects
  • Collaborate with customers, partner-facing engineers, and external scientific collaborators to translate drug design use cases into model requirements


How To Apply:

Incase you would like to apply to this job directly from the source, please click here

Responsibilities

About the job


Federated Drug Discovery AI | Remote-First | €95-115k | Germany

AI Futures has been engaged by the founding team of one of Europe's most technically ambitious drug discovery AI companies to hire a Senior ML Research Engineer. This is a hands-on research engineering role with direct impact on models used in live pharmaceutical workflows.

The company

A venture-backed AI company has built the infrastructure for collaborative machine learning across proprietary pharmaceutical datasets - without any data ever leaving its source. Their federated networks span co-folding, ADMET prediction, and antibody developability, enabling leading pharma teams to train on combined industry datasets while retaining full data control and IP protection.

They are not building demos. Their models run inside real drug discovery pipelines at some of the world's largest pharmaceutical organisations.

The role

As a Senior ML Research Engineer you will drive the development of ML models for molecular and structural biology - from ambitious scientific goal through prototyping iterations to robust tooling used in production drug design workflows.

This is research engineering in a federated environment. You build the model, you build the evaluation that proves it generalises across partner datasets you cannot see in full, and you own the benchmarking when a pharmaceutical partner asks why a binding affinity prediction moved. The hard part is not the architecture. It is making models that transfer across organisations with structurally different data, without centralising any of it.

What you'll do

  • Develop and improve ML models for co-folding, binding affinity prediction, and ADMET modelling.
  • Design rigorous benchmarking and evaluation strategies; define what "good enough" means for a drug design claim and prove it holds across federated partner datasets
  • Diagnose and resolve data quality and pipeline issues that affect model performance across heterogeneous molecular datasets
  • Track the research literature actively and identify state-of-the-art approaches relevant to live projects
  • Collaborate with customers, partner-facing engineers, and external scientific collaborators to translate drug design use cases into model requirements


Loading...