Software Engineer

The role:

• You'll build the data and reasoning behind Codat's Advisory Intelligence Platform, delivered inside the assistant bankers already use.
• It's hands-on engineering: you build it, run it, and own it end to end.

What you'll work on:

• Building the semantic, signal, and reasoning layers that turn client books into advice.
• Creating the agents and MCP servers, with evals that prove they work.
• Owning pipelines and data models from raw source data to the numbers the assistant quotes.

You'll probably have:

• Built production systems from scratch, writing code yourself in C#, Python, or another backend language.
• Served data to an LLM and seen where it goes wrong, with strong SQL, Spark, Databricks, or similar depth.
• Treated your own workflow as something to engineer, using AI for repetitive parts.

How we work:

• Small team, fast-moving, with no return-to-office mandate and hybrid or fully remote options.
• We ship useful things and improve them, trusting you to deliver and not stay online late.