AI Engineer, fine-tuning expert

We are building an AI agent that will ultimately generate a dashboard from financial data. We are looking for an AI Engineer with extensive LLM experience, specifically fine-tuning, to help our finance experts create state-of-the-art dashboard examples we can feed into the agent. We also need to develop a system to evaluate the results and improve them by involving our experts as judges (human-in-the-loop).

 

What you’ll work on

  • Partner with finance experts to define what “great” looks like (KPIs, charts, dashboard layout, insights). 
  • Generate synthetic dataset for experts to work with using existing data samples of real companies.
  • Fine-tune the LLM with the SOTA dashboards that we will prepare
  • Build an evaluation and human-in-the-loop system to improve AI Agent responses.
  • Work on AI agent architecture improvements, including prompt updates and prompt engineering.

 

Nice to have

  • Familiarity with finance dashboards, FP&A, accounting, BI

 

Please include 2 case-studies of LLM fine-tuning or LLM response improvement that you delivered. 

Fine-tuning, AI Prompt Engineering, Reinforcement Learning, AI Agent Development
Published 5 January
142 views
·
24 applications
10% read
To apply for this and other jobs on Djinni login or signup.
Loading...