About this role
Job Description
- Design and build robust data ingestion pipelines, transforming raw CSV/TSV data into structured, queryable datasets.
- Model custom entities and map diverse data sources into standardised target schemas.
- Build and manage data environments using SQLite, Google Cloud SQL and BigQuery.
- Develop and maintain Dockerised services for data loading, embedding generation and data-serving applications.
- Deploy and operate production workloads on Google Cloud Run, with a focus on scalability, reliability and high availability.
- Work across Redis, VPC networking, Artifact Registry and Cloud Storage.
- Implement secure cloud architectures using Cloud IAM, VPC and Cloud Run ingress controls.
- Automate data workflows and deployments through GitHub Actions, including scheduled ingestion, ID mapping, embedding generation and container builds.
- Build and integrate AI-powered capabilities, including natural-language querying, semantic search, embeddings and LLM-powered workflows.
- Contribute to emerging agentic architectures and integrations, including technologies such as Model Context Protocol (MCP).
Qualifications
- 2+ years’ experience in data engineering, cloud engineering or backend development.
- Strong Python development skills, including practical experience with Pandas.
- Solid experience with Docker and containerised applications.
- Strong working knowledge of Google Cloud Platform, particularly cloud compute, managed databases, data warehousing, networking and IAM.
- Strong SQL skills and experience working with both relational and analytical data stores.
- Experience designing, building and consuming REST APIs.
- A strong engineering mindset, with the ability to work independently, troubleshoot complex problems and take ownership from development through to production.
It’s a plus if you have
- Experience with AI/ML engineering, particularly embeddings, Sentence Transformers or LLM applications.
- Exposure to agentic frameworks, MCP or other emerging AI integration patterns.
- Experience with Flask and Jinja.
- Familiarity with WSL and Google Cloud Shell.
Skills
DataPythonSql