Senior Python Engineer Tech / Product · Sheffield

We are seeking a talented and experienced Senior Python Engineer to join our growing AI team. As a Senior Python Engineer at Keystone Education Group, you will play a crucial role in building and optimizing our AI driven hybrid ETL/ELT pipelines and related processes, ensuring the reliability, scalability, and security of our systems. This is an exciting opportunity to work with a talented team of professionals and contribute to the success of innovative products. You will have the opportunity to shape the future of our offerings to over 100 million students a year.

Key Responsibilities:

• Design and implement AI-driven hybrid ETL/ELT pipelines using Python and LLMs: Build scalable ETL workflows that utilize large language models to extract structured and unstructured data from diverse sources such as PDFs, emails, logs, and web content, enhancing data coverage and flexibility.
• Develop intelligent data extraction solutions using NLP and machine learning techniques: Apply LLMs and NLP models to identify, extract, and transform complex data entities and relationships from semi-structured or free-text sources, enabling automation of previously manual processes.
• Ensure accuracy and consistency in AI-powered data transformations: Implement data quality checks, context-aware validations, and post-processing logic to refine outputs from LLM-based extraction, ensuring reliability and business compliance.
• Collaborate with data scientists and AI teams to fine-tune models for domain-specific extraction tasks: Partner with cross-functional teams to train or adapt LLMs for industry-specific data contexts (e.g., education, science, professional development), aligning model behaviour with business needs.
• Monitor and optimize the performance of AI-enhanced ETL pipelines: Track the performance and accuracy of AI components within ETL workflows, and iteratively improve them through feedback loops, prompt engineering, and model selection strategies.
• Document AI/LLM-based extraction logic and ensure ethical data handling: Maintain clear documentation of AI integration in ETL processes, including prompt logic, model usage, and data governance considerations, promoting transparency and responsible AI use.
• Automate ETL pipeline orchestration and data processing workflows: Leverage orchestration tools like Apache Airflow, Perfect to schedule, automate, and manage ETL jobs, reducing manual intervention and improving operational reliability.
• Implement monitoring, alerting, and troubleshooting for data workflows: Set up real-time monitoring, logging, and alerting for ETL and AI components using tools like Prometheus; proactively diagnose issues and ensure system health.
• Ensure data security, privacy, and compliance throughout the ETL process: Apply best practices for secure data handling, including encryption, access control, and anonymization; ensure compliance with regulations such as GDPR or SOC 2.

Qualifications / Requirements:

• At least Bachelor’s degree in Computer Science, Engineering, or a related field. Alternatively equivalent experience is also very desirable.
• Proven experience as a Python Engineer with at least 4 years of experience.
• Strong knowledge of ETL and ScrapeOps principles and best practices.
• Experience using AI/LLMs to extract data from different sources.
• Experience with CI/CD tools such as GitHub Actions, Git or similar.
• Proficiency in scripting languages such as Python & Bash.
• Knowledge of Linux-based operating systems.
• Experience with Amazon Web Services cloud platform or another cloud platform.
• Proven work experience with containerization and orchestration tools such as Docker, Airflow, Prefect and Kubernetes.
• Knowledge of cybersecurity best practices.
• Excellent communication and collaboration skills.
• Ability to work effectively in a fast-paced and dynamic environment.
• Self-discipline and delivery focused.
• Experience mentoring more junior members of your team.

Additional Desirable Skills:

• GraphRAG experience/understanding.
• Experience with dbt.
• Experience using Snowflake (ELT cloud-based data platform).
• Understanding of reverse ETL methods and tools.
• MCP server/client knowledge or Zapier AI Actions experience.

Why Join Us:

• Opportunity to work with cutting-edge technologies and contribute to innovative products.
• Collaborative and supportive work environment with a focus on continuous learning and professional development.
• Competitive salary.
• Exciting career growth opportunities within a rapidly expanding company.

About the team:

The tech team works as an in-house tech department, based out in Stockholm, with the GenAI and Data team based in the UK. The responsibilities of the team encompass developing technical platforms and solutions to lay the ground for the rest of the business at Keystone Education Group. We are a rapidly growing company that is now looking for new talents to strengthen our team.

Do you want to join our family? Please send us your application by hitting the button "Apply here!". We are looking for someone who can start as soon as possible. Keystone is an equal opportunity employer. We celebrate diversity and are deeply committed to fostering an inclusive environment for all employees.