Summer Internship - Software Engineering

About us

At Legora, we’re on a mission to transform the way lawyers work. Our AI-native platform lets legal professionals enhance their productivity and automate complex workflows. We collaborate closely with our clients and iterate at a market-leading pace. In a year, we have gone from an early MVP to tools used daily by thousands of lawyers, and are now scaling rapidly. We are here to win together with our team and clients, and carry the belief that life is too short not to accomplish something truly special.

You are joining an early stage scale-up with exceptional product-market fit, trusted by global leaders like Bird & Bird, Pérez-Llorca, and Mannheimer Swartling. Backed by over $35M in funding from top investors including Benchmark, Redpoint, and Y Combinator. And a a world-class team from Google, Klarna, Spotify, and top tier law firms with infinite room to grow professionally.

The role

This is a unique opportunity to contribute directly to the performance and quality of the AI systems behind our core products. You’ll work closely with both engineers and legal experts to build evaluations that reflect real legal workflows - gaining practical exposure to the legal domain while shaping how our AI systems are evaluated and improved.
You’ll work hands-on with evaluating our AI-systems powering our existing and future products. From designing and building evals, to building new frameworks and metrics, your work will drive key decisions in how we improve reliability and usefulness for our users.

What you will be doing:

• Work with our internal codebase and tools to build, run and iterate on evaluation suites for different products together with the Evals team
• Analyze outputs from agents and subagents, and help summarize findings in reports used by our product and engineering teams
• Be a key voice in how we reason about performance - your work will influence prioritization

Who you are

• Analytical and detail-oriented - you care about edge cases, accuracy, and what “good” really means
• Comfortable with LLMs - you’ve played with prompts, know how to probe, and understand LLMs strengths and limits
• Familiar with Python - you’re comfortable with writing scripts, debug and tinkering with tools
• Curious, creative, and collaborative - you’re energized by solving hard problems with smart people