Software Engineer, Data
Posted 1hrs ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Software Engineer building semantic, signal, and reasoning systems for Codat’s AI-powered banking intelligence platform. Developing data pipelines, LLM tools, and MCP services end to end.
Responsibilities:
- Build the semantic layer of Codat's Advisory Intelligence Platform, including measures, dimensions, and definitions
- Design and build the signal layer that detects changes for clients
- Build and maintain the reasoning layer, including calculations, names, definitions, and structures used by the Codat-side LLM
- Build agents and MCP servers behind the assistant, including tools, failure handling, and evaluations
- Develop pipelines, services, and data models from raw source data to assistant-quoted numbers
- Implement testing, observability, and evaluations to verify data correctness and prevent incorrect model outputs
- Own systems from development through production operation
- Collaborate with engineering, product, and commercial teams to influence product direction
- Build and improve features end to end in a fast-moving small team
Requirements:
- Experience building production systems from scratch, writing code rather than configuring managed services
- Experience serving data to an LLM and understanding issues such as ambiguous definitions, poor retrieval, and lack of evaluations
- Experience working with data pipelines, data shaping, and data-serving systems
- Solid C#, Python, or another backend language
- Depth in at least one of SQL, Spark, Databricks/Delta Lake, Dagster/Airflow/Temporal, or dbt
- Experience with CI/CD, Docker, cloud infrastructure, preferably Azure, and observability
- Experience writing tested code
- Interest in the business implications of data and building appropriate guardrails
- Experience engineering one's workflow with AI automation
Benefits:
- Equity
- Hybrid or fully remote work
- No return-to-office mandate
- Flexible working based on team needs
- Work-life balance with no expectation of staying online late















