Data Scientist – Applied Immunology

JR United Kingdom; Northampton; Hybrid; GBP 40,000 - 65,000; Full time

Job summary

A leading company in the field of applied immunology is seeking a Data Scientist to join their growing team. The role involves analyzing complex immune data, with a focus on developing machine learning models and tools that enhance scientific insights and patient outcomes. Ideal candidates will have experience in data science, particularly within life sciences, and a passion for scientific integrity and innovation.

Qualifications

• 2–5 years experience in applied data science or ML engineering, ideally in life sciences or health data.
• Experience with clean, reproducible Python code.
• Ability to build and evaluate ML models.

Responsibilities

• Own and evolve data pipelines built in Python, R, Kedro, and SageMaker.
• Contribute to modeling projects using ML to identify immune signatures.
• Collaborate with scientists to ensure outputs are actionable.

Skills

Data analysis

Machine learning

Python

Statistical modeling

Reproducibility

Tools

Kedro

SageMaker

AWS

Job description

Social network you want to login/join with:

Data Scientist – Applied Immunology, Northampton

Location: Northampton, United Kingdom

Job Category: Other

EU work permit required: Yes

Job Views: 3

Posted: 04.06.2025

Expiry Date: 19.07.2025

Job Description:

Location: London UK / Hybrid

Team: Data Science | IMU Biosciences

Role Type: Full-time, Individual Contributor (with growth pathways)

About IMU Biosciences:

IMU is building the next generation of immune intelligence—machine learning and AI models that decode the complexity of the human immune system to improve patient outcomes.

We work at the intersection of single-cell technologies, machine learning, AI, and clinical immunology, turning high-dimensional immune data into signatures that inform clinical and translational decisions. Our vision is to build the world’s most insightful immune analytics platform—combining deep biological data and cutting-edge machine learning with rigorous systems-level reasoning.

About the Role

We’re looking for a scientifically curious, systems-minded Data Scientist to join our growing data team. This is a key hire to support the next phase of our platform and product development.

You’ll be joining IMU as an essential part of a team that spans discovery biology, statistical modeling/machine learning, and software engineering—with direct exposure to our clinical collaborators, lab team, and leadership.

This is not a typical “data munging” role.

You’ll help us design, build, and scale how we extract meaning from complex immune data—working on problems like:

• How does immune variation between individuals contribute to outcomes across diseases and treatments?
• How do we unify and exploit complex multimodal large-scale immune datasets?
• Building self-service tools for scientists to interrogate and visualize results easily and safely.

What You'll Do

In the first 6 months:

• Own and evolve pipelines built in Python, R, Kedro, and SageMaker to analyze immune profiles.
• Contribute to modeling projects that use ML to identify immune signatures of disease or treatment outcomes.
• Support internal tooling connecting lab outputs, data cleaning, and model-ready datasets.
• Collaborate with scientists and lab staff to ensure outputs are interpretable and actionable.

In the next 12 months:

• Drive forward components of our immune analytics platform (e.g., prediction, signature interpretation, batch and drift monitoring and correction).
• Help shape standards for data documentation, reproducibility, and metadata management.
• Potential to own specific domains like model validation, ontologies, or scientific interfaces.

You Might Be a Fit If You

• Have 2–5 years experience in applied data science or ML engineering, ideally in life sciences or health data.
• Write clean, reproducible Python and understand workflow tools like Kedro, Dagster, or other orchestration platforms.
• Have built and evaluated ML models for real-world use cases (classification or regression with limited samples).
• Are excited by biological complexity and respect its nuance.
• Think in systems: refactor, generalize, and improve existing code and processes.
• Care about scientific rigor, traceability, and experimental design.

Bonus (not required):

• Experience with flow cytometry, single-cell sequencing, antigen receptor sequencing, or other high-dimensional assays.
• Familiarity with batch effect correction, signal drift, or statistical learning in low-n cohorts.
• Knowledge management systems, ontologies, or scientific metadata experience.
• Experience with AWS/SageMaker, Kedro, Docker, CI/CD pipelines.

What It’s Like to Work Here

At IMU Biosciences, you’ll join a high-trust, low-ego team driven by shared values and impact. We believe in:

• Calm intensity: Working with purpose and clarity.
• Scientific integrity: Following data where it leads.
• Platform mindset: Solving problems once and scaling solutions.
• Cross-disciplinary fluency: Bridging data science, engineering, immunology, and clinical research.

We value autonomy, results, and impact over micromanagement.

How to apply

Send your CV and a short note about why this role feels right to you. Links to code, notebooks, or publications are welcome. We care about your thinking more than polished resumes.

Apply via email to: [emailprotected]. We do not accept unsolicited recruitment agency emails.

More info: https://www.imubiosciences.com/jobs/data-scientist-applied-immunology/