AI/ML Engineer – Legal Tech Platform
anchr · Evergem
Job description
About the role
Contractify and Legile are Belgian legaltech companies in the same group, building a contract-management platform with AI that reads and analyses legal documents. The company is looking for an AI/ML Engineer to own the AI layer: retrieval, orchestration, prompts and models behind document comparison, clause extraction, redrafting and anonymisation, and the evaluation of quality. The role brings in-house the knowledge currently held by external partners.
Key responsibilities
- Retrieval: design chunking and embedding strategies and vector/hybrid search so recall exceeds 85% and latency stays under 500 ms on more than 10,000 Belgian legal documents.
- Orchestration and agents: build workflows chaining LLM steps for document comparison, clause extraction, redrafting and anonymisation, and a multi-agent system that alerts only on important legal and regulatory changes.
- Domain-specific models: create annotated legal datasets with in-house legal experts and test and adapt models for clause comparison, citation accuracy and multi-turn Q&A, deciding with data when fine-tuning beats prompting.
- Prompts and models: version and test prompts and model settings, evaluate new models and decide when to switch.
- Evaluation: build evaluation setups for retrieval quality, hallucination detection and regression testing on real documents.
- Document understanding and integrations: OCR and layout analysis, structured extraction, anonymisation of personal data, and a plugin architecture connecting the AI layer to document management systems.
- Predictive compliance research: explore whether contract data, a graph database and time-series models can flag compliance risks early.
- Internal AI agents: act as technical owner of agents and automations for sales, marketing and customer success, including security and handover when the partner steps back.
- Knowledge: take over AI/ML knowledge from external partners, document it and become the go-to person for LLM, retrieval and evaluation questions.
- AI-native development: use AI coding tools daily and help build shared skills, guardrails and agent workflows.
Required profile
- 3+ years building LLM-based applications, retrieval systems or NLP for real users, with strong Python.
- Hands-on RAG experience: chunking, embeddings, vector search (pgvector or similar), hybrid search, re-ranking.
- An LLM orchestration or agent framework and a view on when not to use one.
- Experience evaluating AI systems: retrieval metrics, hallucination detection, regression sets.
- Comfortable in a production codebase: Git, PR reviews, tests, Docker, cloud.
- Daily use of AI coding tools, with proof they improve speed without lowering quality.
- Pragmatic about AI: able to turn a paper into a working prototype and measure its impact, and able to change prompts and models when the data says so.
- Legal text interests you; a law degree is not required.
- MSc in Computer Science or AI, or equivalent experience.
- English and Dutch.
What we offer
- A competitive salary package.
- Hybrid work, 2 days at the office per week, from the Ghent offices.
- Real R&D, partly funded by Flemish innovation grants (VLAIO).
- A live product with real users from day one, ownership of the AI core and in-house legal experts validating outputs.
- Learning budget for conferences, courses and certifications.
- Part of a larger technology group with career options.
Questions fréquentes
Why are you reporting this job?
Explore further
Salaries, guides and searches in Belgium.
Salaries by job title
Apply in 30 seconds
Enter your email to apply. An account will be created automatically.
By continuing, you accept our terms of use.
Already have an account? Login
A question about this job?
Ask it here: you will get the full job summary by e-mail, right away.
Published 10 hours ago
Expires 1 month from now
8 views · 0 interested
Boost your chances
Upload your CV — we will match you with relevant openings.
Analyzing your CV...
anchr
Evergem