90K–110K GBP / year
Senior Software Engineer (AI/Data)
AIRemote — unknown
Published on 2026-10-28
These details were extracted automatically from the original listing. They may not be complete or fully up to date — it's worth checking the original job post.
About this role
Build the data and reasoning systems behind Codat’s advisory intelligence platform for commercial banking, delivered through assistants such as Microsoft Copilot. The role spans semantic definitions, client-change signals, LLM reasoning, agents, and the pipelines and services that provide reliable financial data.
About the company
Codat is a financial data platform that helps fintechs and banks connect to customers' accounting, commerce, and banking systems.
Stack
C#PythonSQLSparkDatabricksDelta LakeDagsterAirflow
What you'll do
- Build and evolve the semantic layer of measures, dimensions, and definitions used by the assistant.
- Design and implement systems that detect and surface changes in client data.
- Own calculations and structures used by the LLM to generate advice from signals.
- Build agents and MCP servers, including their tools, failure handling, and evaluations.
- Develop data pipelines, services, and models from source data through to assistant responses.
- Add testing, observability, and evaluations to verify data accuracy and catch incorrect model outputs.
- Operate the systems you build and contribute to product direction.
What we're looking for
- Experience building production systems from scratch, with attention to interfaces, failure modes, and maintainability.
- Experience serving data to LLMs and addressing issues such as ambiguous definitions, poor retrieval, and missing evaluations.
- Backend development experience in C#, Python, or another backend language, with tests.
- Strong experience in at least one of SQL, Spark, Databricks/Delta Lake, Dagster, Airflow, Temporal, or dbt.
- Experience with CI/CD, Docker, cloud infrastructure, and observability.
- Interest in business data and designing guardrails when data cannot support a requested answer.
Nice to have
- Experience shaping data tools for model querying, such as a metrics layer, metric views, or an MCP server.
- Experience setting up CI/CD, infrastructure, or observability for a team.
- Use of AI to automate repetitive parts of your own workflow.
Benefits
- Equity