Senior Machine Learning Engineer

Close date: 15th Sept

Competitive Salary and benefits

Cambridge or Gothenburg

About Us

At AstraZeneca we turn ideas into life changing medicines. Working here means being ambitious, thinking big and working together to make the impossible a reality!

About the team

We are a team building, distributing and applying machine learning to biomedical knowledge graphs to transform drug development to be faster and more accurate. Our team is made up of diverse skillsets: data engineers, machine learning researchers and software engineers, all with an interest in graph learning and natural language processing.

We collaborate with scientists across AstraZeneca to help develop better drugs faster, choose the right treatment for patients and run safer clinical trials.

We work with data derived from biomedical literature, public data sources, proprietary clinical and pre-clinical multi-layered data including drug screens, genome-wide analysis, single-cell transcriptomics, proteomics, CRISPR screens, real-world clinical data and Electronic Health Records (RWE, EHR).

Our goal is to move fast, continuously improve and democratize our ability to deliver key biological insights that impact the lives of patients affected by diseases across AstraZeneca's therapeutic areas such as cancer, respiratory and immunology conditions and rare diseases.

We are currently looking for an experienced and creative machine learning engineer to help us solve novel drug discovery problems in collaboration with domain experts and productionize these solutions to reach an ever-growing audience of scientists.

What you'll do

As part of our team, you will develop machine learning models, pipelines and best in class tools that drive our use cases and research. You will contribute to the design of graph recommendation systems that leverage our knowledge graph to suggest biological insight for drug development.

You will contribute to the AI engineering community across our team and other teams working on imaging, deep learning, molecular data and omics by sharing your specialist knowledge and skills.

Partner with Scientists, Data Scientists, Data Engineers and Product Managers across AstraZeneca to build compelling user-facing products.

You will maintain awareness of state-of-the-art applications of knowledge graphs and graph machine learning for drug discovery and influence strategic decisions of the group.

Identify and lead external interactions with opinion leaders in the field and grow our external reputation by publishing innovative methodologies and scientific discoveries.

Finally, you will have the opportunity to work with the latest tech, learn a broad range of skills and be exposed to many exciting challenges in a team that believes in the open-source community, publishing leading research and using modern tech stacks.

What you will need

Essential:

• Independent, collaborative and product focused mindset with a passion for learning

• BSc or MSc in Computer Science, a similar technical field, or equivalent practical experience

• Technical excellence, empathy, and clear communication

• A passion for applying ML to real world problems

• Strong software development skills, with deep knowledge in Python

• Experience coding as part of a team (including participating in PR reviews, establishing unit testing, linting and performance frameworks within CI/CD)

• Experience with a variety of modern ML frameworks, including at least one of PyTorch, JAX, or TensorFlow

• Experience in building, improving and automating pipelines across the full ML development lifecycle

• Experience with UNIX systems, server architectures, and distributed systems

• Experience using cloud environments (Azure preferred)

• Basic understanding of maths and statistics

Bonus points if you have

• Knowledge of the biological or drug discovery domain

• Knowledge of network science

• Experience with recommender systems

• Experience with explainability, causality or reasoning

• Developed machine learning models based on graph data

• A publication track-record in the field of machine learning or any of its applications (e.g NeurIPS, ICML, RecSys, CIKM, KDD, IJCAI, MICCAI, WSDM)

• Experience with graph databases

• Worked in scaling data pipelines on top of modern parallel environments (e.g. distributed clusters, multicore SMP, and GPU)

• Managed workloads on top of Kubernetes clusters

• Worked in designing and exploiting feature stores as part of your data science team

• Built and run machine learning pipelines on cloud services

To give you a better idea of our team, here is a sample of the work we’ve been able to publish and open source.

Research:

• Biological Insights Knowledge Graph: an Integrated Knowledge Graph to Support Drug Development

• Knowledge Graph-based Recommendation Framework Identifies Novel Drivers of Resistance in EGFR mutant Non-small Cell Lung Cancer

• MOOMIN: Deep Molecular Omics Network for Anti-Cancer Drug Combination Therapy

• Explainable Biomedical Recommendations via Reinforcement Learning Reasoning on Knowledge Graphs

Talks:

• RecSys

• NVIDIA GTC

• Spark + AI Summit

Open source:

• ChemicalX

• RexMex

• Awesome explainable graph reasoning

• OntoMerger

Date Posted

Closing Date

AstraZeneca embraces diversity and equality of opportunity. We are committed to building an inclusive and diverse team representing all backgrounds, with as wide a range of perspectives as possible, and harnessing industry-leading skills. We believe that the more inclusive we are, the better our work will be. We welcome and consider applications to join our team from all qualified candidates, regardless of their characteristics. We comply with all applicable laws and regulations on non-discrimination in employment (and recruitment), as well as work authorization and employment eligibility verification requirements.