Staff Data Engineer (Entity Resolution & Identity)

Startup Atlas; Rotterdam; On-site; EUR 110,000 - 150,000; Full time

Job summary

Zeno, the legal AI platform in Rotterdam, seeks a Staff Data Engineer — Entity Resolution & Identity to build core data systems for matching, merging, and versioning entities across jurisdictions.

You will work with large volumes of unstructured data, design durable, explainable systems, and own mission-critical infrastructure with strong ownership and bias toward correctness and performance.

Qualifications

• Staff-level experience in data engineering, solving non-trivial identity, deduplication, or consistency problems.
• Strong system design instincts and ownership mindset.
• Experience building complex, long-lived production systems.
• Strong programming skills (for example Python or similar).
• Hands-on work with unstructured or semi-structured data.

Responsibilities

• Build core entity resolution and identity management systems for the platform.
• Design durable, explainable systems for matching, merging, and versioning entities.
• Ensure performance, correctness, and maintainability of data infrastructure.
• Work with large volumes of unstructured/semi-structured legal data from many sources.
• Provide provenance, replayability, and governance for identity decisions.

Skills

Data engineering

Entity resolution

Python

System design

Data quality

Job description

The intelligence engine for legal work, providing AI-powered legal research, contract review, risk assessment, and drafting tools for in-house legal teams.

Staff Data Engineer (Entity Resolution & Identity)

As a Staff Data Engineer — Entity Resolution & Identity at Zeno, you will build and own core systems for entity resolution and identity management in a legal AI platform, handling unstructured legal data across jurisdictions. This senior role involves designing durable, explainable systems for matching, merging, and versioning entities with a focus on precision, performance, and maintainability.

Job Description

Staff Data Engineer — Entity Resolution & Identity

About the role

As a Staff Data Engineer — Entity Resolution & Identity, you will build and own the core systems that power Zeno’s data and AI platform. Your work sits at the heart of the product: determining what is the same, what is different, what is a version, and how those decisions evolve over time.

This role is centered on hard engineering problems. You’ll work with large volumes of unstructured and semi-structured legal data from many sources, formats, jurisdictions, and time periods. You’ll design systems that can evolve without constant reprocessing, where every decision is explainable, reversible, and traceable.

You operate at senior-to-staff level and take ownership of long-lived, mission-critical infrastructure where correctness, performance, and maintainability matter deeply.

What you’re working on

What you’ll build

• A durable entity resolution framework
• Canonical entities with stable IDs that survive logic and data changes
• Identity graphs with merge/split semantics and full provenance
• Matching and consensus logic balancing precision, recall, and durability
• Incremental recomputation (no “reprocess the world” when logic improves)
• System-level data quality, validation, and observability

You’ll build systems that can reliably answer:

• Are these two records the same real-world legal entity?
• Is this a duplicate, a variant, a new version, or something else?
• How do we evolve matching logic without rebuilding everything?
• How do we make merges reversible and decisions explainable?

Constraints you’ll work under:

• Unstructured and semi-structured legal data
• Conflicting, incomplete, and shifting sources of truth
• Long-lived correctness requirements across jurisdictions

Who you are

• Staff-level experience in data engineering, solving non-trivial identity, deduplication, or consistency problems
• Strong system design instincts and ownership mindset
• Experience building complex, long-lived production systems
• Strong programming skills (for example Python or similar)
• Hands-on work with unstructured or semi-structured data

You think naturally in terms of:

• Entity resolution, record linkage, and deduplication
• Blocking and candidate generation trade-offs
• Precision/recall calibration
• Survivorship and conflict resolution
• Graph connected components and merge cascades
• Versioning, provenance, and replayability

Nice to have

• Experience in legal, government, or other high-complexity document domains
• Experience building human-in-the-loop review systems

Why this roleThis is not a role focused on maintaining pipelines. You will design and build systems that do not yet exist as standard solutions in a domain where data identity, correctness, and evolution over time are exceptionally challenging.

The ride from startup to scale-up means things will break, and there won’t always be a playbook. You’ll wear multiple hats, ship fast, and learn faster. If you thrive on ownership, speed, and building from zero, you’ll love it here.

The ride from startup to scale-up

Things will break, priorities will shift, and there won’t always be a playbook. You’ll wear multiple hats, ship fast, and learn faster. Some weeks will feel chaotic, some problems will feel bigger than your role. That’s the nature of the ride from startup to scale-up: if you need stability and structure, this won’t fit. But if you thrive on ownership, speed, and building from zero, you’ll love it here.

• Be part of a product-driven team reinventing how legal professionals work.
• Join early and shape the foundation of a fast-growing, high-impact startup.
• Work in a place where hierarchy doesn’t matter — only the best ideas do.
• Collaborate with a top-tier team of engineers, researchers, and entrepreneurs.
• Competitive compensation, employee benefits and strong upside as we grow.
• An inspiring place to work in the heart of Rotterdam.