The Team & Environment

• Reporting Line : You will report directly to the Head of Data.
• Team Dynamics : You will work directly with Data Analysts within the Data team and our ML Ops Lead.
• Cross-Team Collaboration : You will also regularly interact with the wider company to ensure technical and commercial alignment across the organisation.
• Hybrid Flexibility : If you live in London or within commuting distance, we’d like you to come into the office at least once a week. If you’re elsewhere in the UK, we ask you to come in once a month and for our Quarterly All Hands.

The Role

In this role as Lead Data Scientist to you will be the individual contributor to the strategic research and methodology that underpins our proprietary metric engine

This position requires a unique blend: the academic rigour necessary to tackle complex sampling challenges, combined with the pragmatic, commercial focus to ensure the delivery of high-value reports within strict deadlines.

Although your main responsibility is independent research, you will operate in a flexible and collaborative setting. To scale your initiatives when necessary, you will have the support of Data Analysts.

Core responsibilities

• Refine Internal Modelling Capabilities: Develop the next iteration of our data modelling, specifically addressing "count balance" (input/output process flows), data gaps and noisy waste stream data.
• Project Execution: Assume accountability for signed deliverables. In an environment where performance metrics vary, your role is to consistently identify and implement methods to extract tangible value. Someone who prioritises actionable insights over theoretical perfection.
• Technical Advocacy: Act as the bridge between raw data science and commercial application, ensuring our methodology is both scientifically sound and commercially viable.

A Day in the Life

• Methodology Research: Leading the research into how we translate frame-by-frame detections into accurate metrics for our proprietary engine.
• Strategic Syncs: Meeting weekly with the Head of Data and ML Ops Lead to present metric engine improvements and areas for focus.
• Contract Delivery: Assuming responsibility for the weekly execution and successful completion of critical, high-value paid contracts (detailed PDF reports and interactive dashboards) with major industry stakeholders.
• Spec Writing: Translating your Python-based research into clear, actionable specs for our ML Ops team to productionise in the pipeline.
• Commercial Handover: Presenting final analyses and internal reports to Customer Success leads, ensuring the findings are easy to understand so they can be refined for the end client.

Success in 6 Months

• Successful delivery of a major paid client report, demonstrating technical accuracy and commercial relevance.
• Implementation of the next iteration of the proprietary metric engine and data modelling framework.

Core Requirements

• Experience : 5+ years in Data Science adjacent roles, ideally working with physical-world data (IoT, sensors, manufacturing, or logistics) where data quality, sample size and fail modes are constant challenges. This includes an ability to identify and present back to stakeholders statistical methods to use.
• Deep Learning Familiarity: A strong practical understanding of the implications of working with data derived from Deep Learning algorithms and the particular nuances of integrating DL output into broader mathematical simulations.
• Toolkit : Deep proficiency in Python for analysis and research.
• Ownership: You don't give up when data is messy. You take the initiative to find workarounds and provide clear paths forward to meet client deadlines. Ability to self-organise and prioritise tasks.
• The Mindset: You are level-headed and a quick learner. You excel when working independently but collaborate effectively when required.
• Master Communicator: Proven ability to translate complex modelling into easy-to-digest methodologies for clients and internal commercial teams.

Bonus

• Experience in the waste industry
• A published academic paper or significant public work (white paper, open-source contribution, or patent) in a quantitative field.