Senior Data Scientist (Clinical Data Analytics)

Story Terrace Inc.
London
1 week ago
Create job alert
About Sava

All the health information we need is within us. Just below the skin. SAVA is redefining the way people interact with their health by developing the most advanced biosensing technology science has to offer, capable of accessing bodily information in a painless, real-time and affordable way.


The Role

We are hiring a Senior Data Scientist (Clinical Data Analytics) to play a central role in the analysis and interpretation of clinical data collected from in-vivo testing of our device. You will be responsible for transforming time-series clinical datasets into actionable insights that inform device performance evaluation and broader company decisions.


The role is highly cross-functional. You will work closely with the clinical team to support trial design and data review and with R&D teams to provide data-driven input on device behavior, performance, and potential failure modes observed in real-world use. A key part of the role is not only quantifying performance, but also identifying and characterising issues or limitations in the data and clearly communicating them.


As our clinical programs expand, the volume and complexity of collected data will continue to grow. This role is therefore critical in ensuring that performance trends and uncertainties are rigorously assessed and communicated at both a technical and high-level summary view. The ideal candidate is comfortable owning analyses end-to-end and can effectively translate detailed statistical findings into insights that are accessible to a broad set of stakeholders across the organisation.


What You'll Do

  • Analyse and manipulate clinical time-series data from in-vivo studies to evaluate sensor behavior, and use additional data sources to perform root-cause analysis when issues are observed.
  • Build, maintain, and improve reproducible analysis pipelines to support scalable processing of clinical data.
  • Investigate data quality issues, performance variability, and potential sensor limitations, and clearly communicate findings to clinical, R&D, and cross-functional teams.
  • Act as a central analytical reference for clinical sensor performance, ensuring that results are interpreted consistently and rigorously across studies.
  • Help establish and evolve methodologies and best practices for clinical data analysis as the company's clinical programs expand.
  • Support long-term product and research decisions by translating complex clinical data into high-level performance trends and risks.

What We're Looking For

  • Degree (MS) in Data Science, Biomedical Engineering, Statistics, or a related quantitative field.
  • At least 4 years of industry experience working with complex datasets, in an R&D environment.
  • Strong ability to analyse and interpret complex clinical and sensor data, with a focus on time-series data.
  • Solid grounding in statistical analysis and modeling, including understanding assumptions and limitations of different approaches.
  • Strong understanding of signal processing fundamentals
  • Proficiency in Python for data analysis, including writing clear and maintainable code for time-series processing and statistical analysis
  • Experience querying and working with relational and non-relational databases to support analysis and reporting
  • Strong knowledge of SQL for data querying, manipulation, and aggregation across large datasets
  • Familiarity with version control systems (e.g., Git) and collaborative development workflows.
  • Experience using data visualisation tools (e.g., Power BI or similar) to communicate insights and performance trends effectively.
  • Strong interest in biomedical and physiological data, with the motivation to understand sensor behavior and underlying mechanisms.
  • Comfortable working in a cross-functional and fast-paced environment, collaborating with clinical, R&D, and other teams.
  • Ability to clearly communicate analytical results, limitations, and trade-offs to both technical and non-technical stakeholders.
  • Proactive mindset, with a sense of ownership over analyses and outcomes

Bonus Points For

  • Experience in biotech companies
  • Previous experience with CGM sensor data or physiological signals
  • Experience in a start-up or scale-up environment

Why Sava?

This is a high-ownership, high-responsibility role in a company that’s building something complex, meaningful, and fast. The expectations are high, the learning curve is steep, and the work is often messy - but the impact is real.


We don't have room for egos or passengers. What we do have is a team of thoughtful, driven, and mission-aligned people who are committed to building something better—and doing it with urgency and integrity.


#J-18808-Ljbffr

Related Jobs

View all jobs

Senior Data Scientist

Senior Data Scientist

Senior Data Scientist

Senior Data Scientist

Senior Data Scientist

Senior Data Scientist

Subscribe to Future Tech Insights for the latest jobs & insights, direct to your inbox.

By subscribing, you agree to our privacy policy and terms of service.

Industry Insights

Discover insightful articles, industry insights, expert tips, and curated resources.

Data Science Jobs for Career Switchers in Their 30s, 40s & 50s (UK Reality Check)

Thinking about switching into data science in your 30s, 40s or 50s? You’re far from alone. Across the UK, businesses are investing in data science talent to turn data into insight, support better decisions and unlock competitive advantage. But with all the hype about machine learning, Python, AI and data unicorns, it can be hard to separate real opportunities from noise. This article gives you a practical, UK-focused reality check on data science careers for mid-life career switchers — what roles really exist, what skills employers really hire for, how long retraining typically takes, what UK recruiters actually look for and how to craft a compelling career pivot story. Whether you come from finance, marketing, operations, research, project management or another field entirely, there are meaningful pathways into data science — and age itself is not the barrier many people fear.

How to Write a Data Science Job Ad That Attracts the Right People

Data science plays a critical role in how organisations across the UK make decisions, build products and gain competitive advantage. From forecasting and personalisation to risk modelling and experimentation, data scientists help translate data into insight and action. Yet many employers struggle to attract the right data science candidates. Job adverts often generate high volumes of applications, but few applicants have the mix of analytical skill, business understanding and communication ability the role actually requires. At the same time, experienced data scientists skip over adverts that feel vague, inflated or misaligned with real data science work. In most cases, the issue is not a lack of talent — it is the quality and clarity of the job advert. Data scientists are analytical, sceptical of hype and highly selective. A poorly written job ad signals unclear expectations and immature data practices. A well-written one signals credibility, focus and serious intent. This guide explains how to write a data science job ad that attracts the right people, improves applicant quality and positions your organisation as a strong data employer.

Maths for Data Science Jobs: The Only Topics You Actually Need (& How to Learn Them)

If you are applying for data science jobs in the UK, the maths can feel like a moving target. Job descriptions say “strong statistical knowledge” or “solid ML fundamentals” but they rarely tell you which topics you will actually use day to day. Here’s the truth: most UK data science roles do not require advanced pure maths. What they do require is confidence with a tight set of practical topics that come up repeatedly in modelling, experimentation, forecasting, evaluation, stakeholder comms & decision-making. This guide focuses on the only maths most data scientists keep using: Statistics for decision making (confidence intervals, hypothesis tests, power, uncertainty) Probability for real-world data (base rates, noise, sampling, Bayesian intuition) Linear algebra essentials (vectors, matrices, projections, PCA intuition) Calculus & gradients (enough to understand optimisation & backprop) Optimisation & model evaluation (loss functions, cross-validation, metrics, thresholds) You’ll also get a 6-week plan, portfolio projects & a resources section you can follow without getting pulled into unnecessary theory.