Senior Data Scientist

The mission for the role: At Popsa, data drives growth, and we’re scaling fast. With over 5 million customers and more joining every week, our data science team plays a pivotal role in this growth by developing and executing the business’ data strategy to build meaningful connections with audiences. We’re looking for a highly skilled and driven Senior Data Scientist who can design, train, and deploy advanced machine learning systems at scale. You’ll work across computer vision, natural language processing, and recommendation problems, training convolutional neural networks on large image datasets, fine-tuning large language models, and optimising for production use both on servers and on edge. You’ll also help design and maintain our FastAPI services that deliver these models into production, collaborating closely with engineers and product teams to build features that directly impact millions of users.  This is a really exciting opportunity for someone keen to be at the cutting edge of generative AI, using machine learning to identify patterns, and develop visualisations to tell compelling data-driven stories for a diverse customer base. Who we are: Joining Popsa right now is pretty exciting. According to Deloitte, we are one of the UK’s fastest-growing tech startups, and in 2022 the Financial Times ranked us in the Top 5 fastest growing software companies in the whole of Europe. We have the backing of some of the best investors in the world. Our native iOS and Android apps are available in 12 languages – attracting more than 5 million users to date – and we ship to over 50 countries around the world. People have never taken more photos than we do today. Our phones are crammed with memories. But although we’re good at capturing moments – we’re not as good at doing anything with them. They’ll often sit forgotten on our devices or in the cloud shrouded in screenshots, receipts and pictures of where we parked the car. Founded in 2016, we’ve already built an award-winning app that’s made printing your memories so easy and accessible, anyone can do it. No more barriers. No more time-wasting. In fact, everything we do as a business is designed with this ethos. We help people turn their best moments into something beautiful and lasting, in no time at all. But this is just the start… 👉 Read more about our journey so far 👉 Check out our Soho office in London Today we’re best known for photobooks, but our vision of the future goes far beyond print. Popsa is building a new generation of services that combine artificial intelligence and thoughtful design to support a healthy processing of the meaningful events and relationships in your life. 👉 Read more about our vision for the future of Popsa Exciting projects

Develop large-scale personalised curation systems that process entire photo libraries, applying computer vision and machine learning to detect events, relationships, and themes, and automatically generate structured “Memories” albums at scale

Apply generative AI across the company - from real customer-facing product features such as title suggestions (look out for our AWS blog coming soon) and captions to internal systems such as customer support

Build and deploy large-scale convolutional neural networks trained on tens of millions of images, with datasets growing daily

Scale inference and serving infrastructure – our FastAPI servers handle millions of requests in production

Core responsibilities

Design, train, and deploy Machine Learning models that directly impact customers every day

Clean, transform, and prepare data for analysis, handling missing values and inconsistencies to ensure reliability

Own the full stack of data science development: from prototyping models to production deployment and monitoring

Extract insights from large, complex datasets (structured and unstructured) to identify trends, build predictive models, and develop algorithms for creative applications

Collaborate closely with product, engineering and marketing teams to ship features end-to-end

Contribute to improving infrastructure for large-scale training, testing, and evaluation

Present data findings and insights in a meaningful and visually compelling way to technical and non-technical stakeholders, including creative teams and leadership 

Design and conduct statistical experiments to evaluate creative strategies and optimise outcomes

Continuous Learning - stay updated on the latest advancements in data science, software, and tools, and knowledge share

Key experience

Excellent coding ability in Python

Solid experience with SQL

Strong understanding of statistics, data mining, and predictive analytics techniques 

Hands-on experience with Docker and Terraform

Exposure to AWS (e.g. S3, ECS, SageMaker, EC2)

Experience deploying and testing generative AI models in production

Comfort with engineering-heavy workflows (CI/CD, containers, infrastructure)

Experience developing and applying various machine learning algorithms, including classification, regression, and clustering

Excellent verbal and written communication skills to effectively convey complex findings and stories to diverse audiences

Analysis of user data to personalise content, improve engagement, and optimise user journeys

Experience with recommender systems

Familiarity with large-scale training pipelines (distributed training, GPU scaling)

Experience with multi-head CNN architectures or multi-task learning for robust model training

Contributions to open source, technical talks, or side projects showing initiative