Data Scientist
Role details
Job location
Tech stack
Job description
You will work closely with Product Engineering, Analytics and Business stakeholders to diagnose data artefacts, run experiments, and provide clear, defensible improvements that can be deployed to production. Strong statistical reasoning and ML foundations and a pragmatic, outcome-driven mindset are essential., Analysis & Research
- Analyse Meshh's existing Wi-Fi event datasets to identify randomisation patterns, biases, and data loss characteristics
- Design and develop contextual evaluation methodologies in order to define what good looks like.
- Evaluate and test promising approaches from recent research and industry practice.
Modelling & Mitigation
- Design statistical or probabilistic models
- Validate models using historical data, controlled assumptions, or synthetic datasets
Validation & Communication
- Clearly document assumptions, limitations, and confidence intervals
- Produce concise, decision-oriented outputs for product and leadership stakeholders
- Advise on which approaches are suitable for production vs. reporting-only usage
Collaboration & Handover
- Work closely with Meshh's engineering and analytics teams to ensure feasibility
- Provide working implementation of pipelines, production-ready code and evaluation harnesses/dashboards.
- Support knowledge transfer as solutions move toward production, OverviewLocation:Sheffield (2 days per week/ Hybrid) Reporting to:VP of Engineering The Team:2 Data Scientists, 1 Data Engineer IntelliAM is an intelligent asset management company specialising in industrial IoT data. We ingest high-frequency factory and sensor data, apply...
Requirements
We are seeking an experienced and highly skilled Data Scientist / Applied ML Engineer to lead the implementation and experimentation work for Meshh's Wi-Fi analytics project. This is not a greenfield build - you will inherit a working ML pipeline and evaluation system and be expected to understand it quickly, identify its limitations, and make targeted improvements that meaningfully improve accuracy and robustness., * Strong foundations in applied data science and machine learning
- Experience working with large, noisy and incomplete datasets
- Proficiency in Python (NumPy, pandas, SciPy, scikit-learn or equivalent)
- Strong statistical reasoning and ability to defend methodological choices
- Experience turning analytical work into practical, business-relevant outcomes
- Highly structured and methodical way of working with clear communication, documentation etc.
Highly Desirable
- Familiarity with AWS services (Sagemaker, ECS, Fargate) and cloud-deployed ML pipelines
- Experience with GPU-accelerated data processing
- Experience building production-grade unsupervised learning on medium-dimensional structured data.
