Senior Data Scientist | Personalized Medicine | Deep Tech Startup in London

At i Lo F, you will develop data science methods that extract reliable signals from biomedical and optical data.

The role sits at the intersection of modelling, signal processing, and experimental science, with a focus on noisy, high-dimensional, and biologically complex datasets.

You will work with raw data generated on in-house instruments, helping improve signal quality, acquisition protocols, and hardware performance.

You will also apply chemometric and multivariate methods to spectroscopic data such as Raman and FTIR, turning complex measurement signals into more reliable and interpretable insights.

You will work closely with experimentalists, hardware specialists, and product teams, directly influencing experimental design, data interpretation, and technology development — creating a tight feedback loop between theory and practice.

This is a high-impact role in a growing team. We are looking for someone who combines technical depth, scientific rigour, and strong execution in a fast-moving environment.

This is a hybrid role with onsite training and a minimum of 5 days per month on-site. Greater on-site availability is a plus.

Job Description

• Own the full data science workflow for specific projects, from problem framing to delivery.
• Analyse proprietary biomedical datasets to identify patterns, variability, and opportunities for improved performance.
• Develop statistical and machine learning methods for noisy, high-dimensional, and often small-sample data.
• Design and evaluate robust validation strategies, including uncertainty and robustness checks.
• Improve preprocessing pipelines, signal quality, and acquisition protocols through work with raw data and instrumentation.
• Apply chemometric and multivariate analysis to spectroscopic data.
• Work cross-functionally with experimental, hardware, and product teams.
• Communicate findings, trade-offs, and recommendations clearly to technical and non-technical stakeholders.
• Contribute to reusable analysis frameworks and internal best practices.
• Stay up to date with the latest advancements in data science, computational modeling, and advances in spectroscopy for clinical applications.
• Contribute to research publications, patents, and presentations at leading conferences.

Who we are looking for?

You are a hands‑on Data Scientist who is comfortable working in a fast‑paced startup environment and tackling complex scientific problems with real analytical consequences.

You move fluently between exploratory analysis, statistical modelling, signal processing, and practical delivery.

You have experience with biomedical, spectroscopy data, or with other high‑dimensional data where noise, batch effects, measurement artefacts, and instrument-driven variation must be handled carefully.

You are strong in experimental design, validation strategy, and communicating uncertainty, trade‑offs, and limitations clearly.

You work well in interdisciplinary teams and enjoy collaborating with scientists and engineers across biology, hardware, and product.

You care about scientific rigour, execution speed, and turning complex data into models and insights that can make a real difference.

Qualifications

• Ph D in Computer Science, Applied Math, Statistics, Physics, Engineering, or a related field.

Exceptional candidates with a Master’s degree and strong research experience will also be considered.

• 3+ years of post-Ph D experience in academia or industry working on quantitative data problems.
• Strong experience in applied statistics, predictive modelling, and experimental design.
• Experience working with raw data alongside instrumentation, including optimisation of signal quality, acquisition protocols, or hardware performance.
• Plus: Experience in chemometric or multivariate analysis of spectroscopic data such as Raman, FTIR, or related high-dimensional signal data.
• Strong data preprocessing, feature engineering, and exploratory analysis skills.
• Experience designing robust validation strategies and interpreting model performance in ambiguous or noisy settings.
• Strong problem‑solving ability and comfort with incomplete, messy, or evolving data.
• Excellent written and verbal communication skills.
• Experience mentoring junior team members is a plus.

This is a unique opportunity to work on high‑impact projects at the intersection of theory and experiment, developing models that shape cutting‑edge technology and scientific discoveries.

#J-18808-Ljbffr