(Senior) AI Product Engineer (m/w/d)

Pegel; Berlin; Hybrid; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Public transport fully covered

Company pension with 20% employer conr

Corporate benefits platform with brand

Dog-friendly office

Regular company and team events, after

Free drinks, fresh fruit, and granola

Job summary

LegalHero in Berlin is seeking a Senior AI Product Engineer to identify and build AI-enabled legal workflows. You will run independent AI projects, prototype rapidly, and hand off mature features with thorough documentation and handover plans.

You’ll also support squads with feasibility, costs, and risk assessments, ensuring GDPR and compliance considerations are addressed. You’ll collaborate with attorneys and Legal Ops, report to Product Leadership, and work in an office-first setup with 3

Qualifications

• Multiple production-ready AI/LLM systems that you’ve shipped to real users and taken responsibility for
• Demonstrable product ownership from a vague problem to a finished product
• Strong Python skills and solid software engineering foundation (Git, testing, CI/CD, code review)
• In-depth experience with LangGraph, LangChain, or similar
• Proficiency with LLM provider APIs: function/tool calling, structured outputs, streaming
• Evaluations, golden datasets, and guardrails before deployment
• Solid prompt engineering - you know when to use which technique
• Business-level English; German is a major plus due to our legal domain

Responsibilities

• Independent AI projects (about half of your time)
• Identify high-impact AI opportunities in our legal workflows
• Validation with attorneys, Legal Ops, and insurers; prototypes built in days
• Bring winning solutions into production: routing, chaining, summarization, and agent-based loops
• Hand off mature features to the squad with documentation, evaluations, and a handover plan
• Support the squads in feasibility, costs, model selection, risks
• Design evaluations, golden datasets, and guardrails
• Review concepts before roadmap inclusion, including prompt injection and GDPR compliance
• Advance AI best practices: prompt engineering standards, LLM observability, agent-based coding workflows

Skills

Python

Product ownership

Software engineering basics

Prompt engineering

LLM observability

Guardrails

Stakeholder communication

Tools

LangGraph

LangChain

Git

CI/CD

LLM APIs

Job description

• Central location between Gleisdreieck and Potsdamer Platz

What You’ll Do

You’ll identify open AI opportunities, build them from start to finish, and bring them to real users. As a Senior AI Product Engineer, you’ll work across our three product squads: You’ll single-handedly turn unaddressed topics into products, hand them off once they’re up and running, and serve as a sparring partner for the squad PMs on all AI-related topics. For us, “senior” refers to your approach to work, not your years of experience. You’ll report directly to Product Leadership.

Your Responsibilities

• Independent AI projects (about half of your time)
• You’ll identify high-impact AI opportunities in our legal workflows - in areas where no specific squad is responsible
• Validation happens quickly: discussions with attorneys, Legal Ops, and insurers; prototypes built in days
• You’ll bring the winning solutions into production yourself: routing, chaining, summarization, and agent-based loops
• You’ll hand off mature features to the squad - complete with documentation, evaluations, and a handover plan

Support for the squads (the other half)

• Feasibility, costs, model selection, risks: You’ll answer these questions before every AI feature is launched
• You support the teams in designing evaluations, golden datasets, and guardrails
• You review concepts before they go into the roadmap - including prompt injection and compliance risks (GDPR, Section 203 of the German Criminal Code)
• You advance AI best practices: prompt engineering standards, LLM observability, and agent-based coding workflows

What you bring

Must-have

• Multiple production-ready AI/LLM systems that you’ve shipped to real users and taken responsibility for - no prototypes
• Demonstrable product ownership: from a vague problem to a finished product
• Strong Python skills and a solid foundation in software engineering (Git, testing, CI/CD, code review)
• In-depth experience with LangGraph, LangChain, or similar - including an understanding of what’s happening under the hood
• Proficiency with LLM provider APIs: function/tool calling, structured outputs, streaming
• Evaluations, golden datasets, and guardrails before deployment
• Solid prompt engineering - you know when to use which technique
• Business-level English; German is a major plus due to our legal domain

Soft Skills

• The maturity to work without a squad around you: You set your own priorities and know when to say no
• You can explain a technical trade-off to a lawyer and a legal workflow to an engineer

What we promise

Work Environment & Flexibility

• Office-first: 3 days in the office, 2 days working from home - with flexibility in how you structure your work
• Modern, air-conditioned office with plenty of natural light and a large rooftop terrace overlooking Berlin
• Central location between Gleisdreieck and Potsdamer Platz

Benefits

• Full coverage of the public-transport ticket
• Company pension plan with a 20% employer contribution
• Corporate benefits platform with discounts from many brands
• Dog-friendly office
• Regular company and team events, after-work fun with Switch, PS5, darts, and foosball
• Free drinks, fresh fruit, and granola

Culture & Collaboration

• Agile mindset with open communication - every voice countsFeedback is part of our culture - we believe in growing together

Your contact:

Nadine · HR Manager · [e-mail] · 030 22957522