Our client the Competition and Consumer Protection Commission (CCPC) is seeking a Data Engineer.
Division Overview
The Forensic Technology & Data Analytics Division (FTDA) supports all other Divisions within the CCPC, particularly the Enforcement Divisions, in the areas of Digital Forensics, eDiscovery, Open-Source Intelligence and Data Analytics. The Division has recently undergone an expansion with the full transformation of laboratory systems and technical capabilities.
You will be an integral part of the Forensic Technology and Data Analytics (FTDA) team, comprising a Director (Principal Officer), two Deputy Directors (AP1) and one FTDA Senior Analyst (HEO).
The Role:
We are looking for a Data Engineer with a passion for building intuitive, user-friendly applications to help our investigation teams. Your work will empower investigators to make informed decisions and identify potential breaches of competition and consumer protection law, as well as breaches of other legislation falling within the CCPC's remit. You will get to work closely with our enforcement teams to understand key indicators and ensure the applications align with enforcement goals.
Your goal will be to simplify complex NLP methodologies into accessible, actionable insights for our Enforcement Divisions.
In this role your work will initially support the role of the CCPC's Forensic Technology & Data Analytics Division
(FTDA) on the following cross divisional projects:
• Screening for bid rigging - detection of collusion in public tendering processes
• Price Indication Directive - Online price monitoring
The Successful Candidate:
In addition to the immediate appointment from this campaign, an order of merit may be established. This may be used to fill any future vacancies at the same level within this or other Divisions of the CCPC where roles have similar responsibilities and/or similar skills are required.
The Successful Candidate is as follows:
• Comfortable working on own initiative.
• Works well with others as part of small team.
• Enjoys the opportunity to develop best practices and input into full development lifecycle.
• Finds new and better ways of doing things.
• Interested in upskilling and education.
• Dedicated to ongoing research and development in areas of expertise.
• Takes a leading role in project management and is comfortable giving input.
• Appreciates the opportunity and importance of diversifying skills in other areas of computer science and data science.
Key Responsibilities:
• Develop User-Friendly NLP Tools that can analyse large datasets of public tender documents and vendor communications to identify potential collusion or anti-competitive behaviour.
• Pattern Recognition & Anomaly Detection: Use NLP algorithms to detect suspicious patterns in the language, tone, and structure of bids, proposals, and other tender-related documents, flagging possible signs of collusion such as identical language, unusual bid behaviours, or coordinated pricing strategies.
• Develop NLP Tools for Price Monitoring: Build and deploy NLP-based tools to extract and analyse pricing information from various e-commerce platforms, websites, and online marketplaces.
• Simplify NLP for Non-Technical Users: Ensure that the NLP models and results are presented in an easy-to[1]understand way for non-technical end users, including visualization dashboards, simple reports, and intuitive interfaces that highlight key insights and potential red flags.
• Model Development & Optimization: Develop, fine-tune, and evaluate NLP models for tasks like text classification, sentiment analysis, entity recognition, and similarity detection, with a focus on identifying unethical practices.
• Data Preprocessing & Feature Engineering: Develop robust text preprocessing pipelines that clean and prepare large volumes of unstructured text data (e.g., bids, contracts, emails) for analysis.
• Opportunity to travel and liaise with National and International experts to help solve problems.
• Opportunity to assist the FTDA team in the areas of Digital Forensics, eDiscovery and Open Source Intelligence.
• Opportunity to test and develop in-house Gen AI tools.
Essential:
• Education: Bachelor's or Master's degree in Computer Science, Data Science, or a related field.
• Proven Experience: 2+ years of experience in developing NLP tools and models, ideally for business applications, and with a focus on user-friendly interfaces.
• Programming Skills: Strong proficiency in Python, including experience with NLP libraries such as NLTK, SpaCy, Hugging Face Transformers, or similar.
• Communication Skills: Strong verbal and written communication skills to present complex technical concepts in an accessible and clear manner for non-technical stakeholders.
• User-Centric Design: Experience in developing software or tools with a strong focus on usability, ensuring the tool is intuitive for non-technical users.
• NLP Expertise: Deep understanding of NLP techniques for tasks like text classification, entity recognition, semantic analysis, and pattern detection.
Desirable:
• Problem Solving: Ability to understand the nuances of public procurement processes and translate them into actionable insights through NLP and machine learning.
• Experience with Data Visualization: Familiarity with data visualization tools (e.g., Tableau, Power BI, or custom dashboards) to present findings in a non-technical, actionable manner.
• Cloud and Scalability: Experience deploying NLP solutions on cloud platforms (e.g., AWS, Azure, Google Cloud) for scalability and production readiness.
• Experience with container orchestration (e.g., Docker, Kubernetes)
Application Process:
To apply for this role using the link on the CCPC careers page, please submit an up-to-date CV and a cover letter, max 500 words, outlining your experience relating to the key responsibilities of the role. Applicants should note that canvassing will result in your exclusion from the process.
This role will close on Wednesday, 28th May at 3pm.