Senior Data Scientist - Manchester Area, United Kingdom - Mobysoft

Description

Senior Data Scientist

Mobysoft is one of the fastest growing SaaS providers in the UK and has been shortlisted in the "Top 50 fastest growing technology companies in the North" for four successive years. Mobysoft provides predictive analytical software that has helped our customers deliver tens of millions of pounds in savings. Such is our success; customer numbers have doubled in little over two years and as a result we're looking for great people to join our exciting team.

Role overview

We are an ambitious, customer-centric Data & Insights team, dedicated to developing a new generation of data products that unlock significant value for the social housing sector. We operate with a focused product lens, driven by curiosity and a commitment to technical excellence.

Data Science is pivotal to this mission. As a Senior Data Scientist you will take a leading role in researching, building, deploying and monitoring machine learning (ML) models, in close collaboration with cross-functional teams. Your efforts will support our clients through enhanced decision-making and automation, utilising our developing cloud-based AWS data platform. As part of this we'll also ask that you liaise with our clients (directly or through events, conferences, webinars etc.), to help support their data driven journeys.

As such we are looking for a stellar Senior Data Scientist (SDS) professional to join our dynamic team, working with our brilliant data scientists, and alongside our superb data engineers, and data analysts.

What will you be doing :

• Applying natural language processing (NLP) techniques (including applications of localised large language models - LLMs) to free text data. For example, what features can we construct from content provided by trades persons to train models to ensure effective property repairs?
• Can we consistently extract sentiments from free text tenant responses to support the measurement, reporting and directed improvement of tenant satisfaction
• Working with data engineering to determine how we best represent network data within a graph database? What features can we detect and model from this? For example, in support of minisming repeating repair jobs at the same property.
• Generating forecasts from timeseries data using traditional (e.g., ARIMA) and newer approaches (e.g., transformers) to help clients understand and better prepare for rent payment fluctuations.
• How can we cluster repair jobs to provide root cause insights and next best actions.
• Building recommendation systems, including testing reinforcement learning approaches, to support optimised rent collection
• Taking labelled data and supervised learning approaches, to generate optimal contact strategies for multi-channel tenant engagement
• partner internet of things (IoT) sensor data with existing asset data to drive new insights into pressing maintenance issues, such as damp & mould
• Exploring the use of generative AI to transform service delivery such as building report commentary, enhancing product engagement and producing synthetic data
• Linking insights from many of these experiments to prescriptive/next best actions, using optimisation and simulation techniques.

Please note this is a professional, technical role, with no line management responsibilities. There will however be multiple opportunities to lead data science workstreams.

Why should you consider this role?

Alongside the work opportunities as described your development will be supported, you will be sensibly renumerated, we will provide a compelling benefits package and we are a great bunch of folks to work with - though we would say that

What qualifications and experience are we after?

• Ideally a Masters degree in Data Science, Machine Learning, Artificial Intelligence, or similarly related and quantitative discipline. Merit and above would be great.
• Circa 5+ years of serious commercial experience working on a range of complex problems, across varied data types and machine learning (ML)/artificial intelligence (AI) approaches*, with multiple live solution deployments.
• Proven ability to successfully tackle a broad swathe of our interesting problems catalogue. Of course this includes an excellent familiarity with the data science process: experiment/hypothesis formation, data selection, feature engineering, model selection, sampling/cross validation, hyperparameter tuning, model performance metrics, effective code and notebook documentation.
• Experience of working in a Cloud environment (we use AWS to run an EMR based platform), including experience of scaling ML solutions using Spark.
• Experience across common supervised, unsupervised, semi-supervised, reinforcement machine learning techniques

What technical skills are required

• Accomplished Python coder.
• Data wrangling and data engineering excellence using primarily Python and SQL across structured, semi-structured and unstructured data.
• Ability to use dimension reduction techniques (PCA, encoders etc.)
• Excellent familiarity with elastic net logistic regression, random forest and XGBoost ensembles to work on supervised problems with structured, tabular data. We currently use Scikit-learn, and we're open to suggestions for additional libraries.
• Classification using K-means, K-Medoids or similar and the skills to evaluate solution suitability e.g., Silhouette Score.
• Confident in the skills needed to deploy deep learning, ideally through Tensorflow, including transformer architectures.
• Natural language processing capabilities, including skills in sentiment analysis and using and localising large language models (transformers), ideally through the Hugging Face platform to understand and match similar texts.
• Maths skills and knowledge to get these techniques at a fundamental level in order to devise novel applications.
• Forecasting using time-series and related approaches, solved using classical (ARIMA) and modern (transformer based) techniques.

We appreciate this is quite a list. We don't believe in Unicorns, we do believe that anything here that you are not skilled in will be picked up quickly (weeks) given your coding, maths and problem solving abilities. We invest heavily in our people and will provide training - it's the people that make our business

What experience and technical skills are desirable

• in deploying graph analytics
• and previous application of deep feature synthesis frameworks for feature engineering
• of working with transactional data

Benefits

Competitive salary and rewards package including: - Private Health care , 4 x salary Life cover, 25 days annual leave, increasing to 28 after 3 years service ,salary sacrifice pension scheme and much more ..

Inclusion

We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, colour, national origin, sex, gender, gender expression, sexual orientation, age, marital status, veteran status, or disability status. We will ensure that individuals with disabilities are provided reasonable accommodation to participate in the job application or interview process-please contact us to request accommodation. We offer hybrid roles, so we're happy to discuss flexible working

If you are interested and would like to know more then please apply ASAP to or via our careers page.