Infact are a progressive, fast-moving, credit referencing start-up. We see great opportunities to combine foundational statistics with modern AI to find meaning in consumer finance data.
Candidates should take the time to read all the elements of this job advert carefully Please make your application promptly.
We are looking for a hands-on Data Scientist to work alongside our lead data scientist to experiment, engineer, and deliver innovative predictive models into our modern AWS production environments.
The Technical Reality: We operate a pragmatic stack where Linear Regression remains vital for stability and baseline performance, while XGBoost and LLMs are used as responsible additions. We are looking for someone who knows when to use a simple linear model and when to deploy and how to explain complex non-linear and generative AI.
Current Areas of Focus: Affordability, income and expenditure analysis, credit risk, and fraud detection, with excellence in Entity Resolution – tying together disparate consumer data into a holistic view.
Your work will directly help traditionally underserved consumers to access the most suitable financial products, whilst supporting our customers in discovering good responsible actors and highlighting potential risks from others.
Responsibilities
- Predictive Modelling (Linear & Non-Linear): You will build and maintain foundational Linear Regression models for credit, affordability, and fraud scoring, while developing advanced XGBoost models for deeper risk insights. You will mine data to find behavioural signals—such as spending volatility or income stability—that predict affordability, repayment, and fraud risk.
- NLP & Entity Resolution: Use classic NLP techniques (fuzzy matching, named entity recognition) to normalise, cleanse, and match and consumer identity data at scale.
- Generative AI & Explainability: Utilise LLM APIs for advanced context engineering on unstructured data, while using models such as SHAP to ensure that every model we build is fair, free from bias, and explainable to consumers, customers, and regulators.
- Engineering & Deployment: Work within the engineering team on MLOps to containerise, deploy, and monitor models in high-scale production.
Skills & Requirements
Core Data Science:
- Foundational Stats: You must have an excellent grasp of Linear and Logistic Regression. You understand the assumptions, limitations, and interpretability of these models.
- Advanced ML: Experience with boosting models is essential for our higher-complexity tasks.
- Analytics Patterns: A core ability to creatively analyse a raw dataset and spot trends, outliers, and behavioural clusters without needing a pre-defined hypothesis.
- Explainability: Experience using SHAP or similar frameworks to explain model outputs.
Natural Language Processing (NLP):
- Entity Matching: Experience with deduplication, record linkage, or entity resolution.
- GenAI: Experience with LLM APIs and Context Engineering (constructing prompts, managing context windows, evaluating behaviour).
Engineering & Stack:
- Python: Expert level (Pandas, NumPy, Scikit-Learn).
- Data Engineering: Strong SQL skills and experience building data pipelines.
Experience:
- Education: Degree in a quantitative field (Statistics, Mathematics, Computer Science, etc.).
- Industry: 2+ years of experience in Fintech, Finance, or Credit Risk is required.
- Profile: You are an ambitious candidate who wants to grow. You are comfortable working remotely but value team collaboration.
The Setup
- Location: Primarily remote and flexible, collaborating in the central London office at least 2 days per week. xwzovoh
- Culture: As a small, progressive team, we offer the agility to move fast and the autonomy to lead your own projects.
- Diversity: We are committed to creating a diverse environment and we are proud to be an equal opportunity employer considering candidates without regard to gender, sexual orientation, race, colour, nationality, religion or belief, disability, or age.
See for more details about us.