Senior AI / Data Engineer (Legal tech - AWS)

Wymagania:
About LEXA

LEXA is an AI legal research assistant with up-to-date knowledge of Hungarian, Polish and EU law. Users ask legal questions in their own words. LEXA answers in minutes and links every law and court decision it cites to the original source, so each answer can be checked right away.
- 4.3M+ legal documents: legislation, Hungarian, Polish and EU court decisions, decisions from 30+ authorities, legal articles and historical versions of laws- Built for lawyers, in-house counsel, law students and businesses- Works where users already are: in the LEXA app and as a ChatGPT / Claude extension
Our mission is to reduce lawyers' cognitive load, so they can focus on the work that needs creativity, judgement and strategy. We believe high-stakes fields like law are best served by domain-specific AI and search, not general-purpose models. LEXA was founded by a a data scientist who specializes in LLMs and large-scale text processing, and a lawyer with 15+ years of experience in tech law. We're now expanding rapidly into new countries.

The role

This is a foundational role in our AI and data services team. You'll own the data and retrieval layer behind our AI agents. That covers the scrapers that collect legal sources, the search tools our agents use to find them, and the agentic framework that ties it all together. The architecture, standards and practices you set will be what the team builds on.

What you'll do
- Build and maintain robust, scalable scrapers for legal sources across multiple countries- Design and build search and retrieval tools for AI agents- Develop and evolve our agentic AI framework- Architect AWS data pipelines that ingest, process and manage large volumes of legal text- Develop, deploy and maintain production services on AWS, fully defined as Infrastructure as Code- Work spec-first: write clear specs, direct AI coding agents, and review every change for correctness, quality and security- Help us onboard new countries fast as we expand
Must-have
- Strong programming fundamentals and 5+ years of experience with Python- 7+ years of experience in data engineering, with a strong focus on text data- Excellent AWS knowledge: developing, deploying and maintaining production services- Strong command of AWS data engineering principles, including architecting reliable, scalable data pipelines and data management solutions- Robust knowledge of Infrastructure as Code (e.g. Terraform, AWS CDK, CloudFormation)- AI-native development: you already write essentially 100% of your code with AI- Working knowledge of spec-driven development and agentic loops as part of your daily workflow- A reviewer mindset: you act as a code reviewer rather than a code writer, and you know how to move fast with AI without introducing bugs or security vulnerabilities
Strongly preferred
- NLP background- AI engineering and/or data science experience (LLM applications, RAG, AI agents)
Bonus
- Advanced AWS networking with a security focus: designing secure VPC architectures (private subnets, least-privilege security groups, VPC endpoints / PrivateLink), controlled outbound traffic, and network monitoring (e.g. VPC Flow Logs)
Why join us
- Foundational role: you'll shape our AI and data services from the ground up- Real ownership: your compensation combines a base salary and equity- Real impact: the tools you build power how lawyers do their research- Rapid growth: you'll help take LEXA into new countries- AI-native engineering: spec-driven, agent-powered development is how we work every day, not an experiment
Details
- 📍 Location: Budapest 6th district, Hybrid, 2 office days per week - 🕒 Type: Full-time- 💰 Compensation: base salary + equity based on experience