Software Engineer III – DataPilot – Data Solutions

at  FactSet Research Systems

Software Engineer III – DataPilot – Data Solutions
Join the DataPilot team at FactSet, where our mission is to transform our users’ natural language queries into actionable insights using our generative AI platform. Core to the DataPilot infrastructure is a knowledge graph that connects financial concepts to the data available at FactSet. Engineers on the team maintain and enhance a GenAI-powered software stack that operates at the intersection of financial data, knowledge management, and data engineering.
Team => 3 software engineers in London and 3 software engineers in the USA.
Technical stack => Python, pandas, Jupiter, typescript, terraform, AWS, Lang chain, Open AI, Neo4j, streamlit, pydantic, graphQL.

The day-to-day role of an engineer on the DataPilot team is to:

• Enhance the knowledge graph model to improve answer quality on complex queries.
• Integrate additional datasets into DataPilot based on user workflow needs.
• Design, implement, and deploy DataPilot services and infrastructure.
• Monitor and enhance the accuracy, performance, and observability of our GenAI RAG stack.
• Evaluate new large language models, tools, and AI engineering techniques
• Improve query planning, optimization, and evaluation infrastructure.
• Partner and collaborate with product development leads to identify technical requirements for future product enhancements.

You will be working on a team in a fast-paced environment where you will have the opportunity to influence the design and architecture of the product. An ideal candidate for the role would be an individual that has experience or a strong interest in working with generative AI and related technologies, utilizing open-source
composable data frameworks
, an interest in knowledge graph and semantic web technologies, and a passion for understanding and iterating on user workflows.

Required Skills

• Proficiency in Python, TypeScript, or similar language and its environment (3+ years of experience).
• Familiarity with relational databases and data modeling techniques. (3+ years of experience).
• An interest in financial technology.
• Strong technical writing skills.
• Familiarity with API design.

Additional/Desired Skills

• Experience with graph databases
• Experience with data governance
• Experience with Generative AI frameworks and platforms (e.g. LangChain, LlamaIndex)
• An interest in the financial services domain

Education
Bachelor’s degree in computer science, computer engineering, or similar technical field or equivalent practical experience

• Enhance the knowledge graph model to improve answer quality on complex queries.
• Integrate additional datasets into DataPilot based on user workflow needs.
• Design, implement, and deploy DataPilot services and infrastructure.
• Monitor and enhance the accuracy, performance, and observability of our GenAI RAG stack.
• Evaluate new large language models, tools, and AI engineering techniques
• Improve query planning, optimization, and evaluation infrastructure.
• Partner and collaborate with product development leads to identify technical requirements for future product enhancements