AI Engineer

Description

At Omnilex, we’re on a mission to transform the way lawyers work. Our AI-native platform lets legal professionals enhance their productivity in legal research and automate 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 a product used daily by thousands of legal professionals at our clients in Switzerland, Germany and Liechtenstein - and are now scaling rapidly across Europe.

You’ll be joining a young, passionate, and dynamic team of 15, with roots at ETH Zurich.

As an AI Engineer – Legal Search Optimization, you will focus on building and shipping retrieval, reasoning, and context engineering that powers our legal research experience.

Responsibilities

• Retrieval & ranking: Implement and iterate domain-specific retrieval and reranking algorithms going beyond the standard ones, including knowledge graphs and custom workflows
• LLM-powered products: Design and build robust, production-grade LLM systems and chatbots
• Signals & features: Design scoring features from citations, authority, recency, jurisdiction, section/paragraph structure, and intra-doc anchors
• Practical considerations: Carefully evaluate decisions like API vs. self-hosted; add batching, early-exit, and caching to control cost/latency
• Evaluation that guides shipping: Define offline eval sets, run quick ablations, and watch production feedback and dashboards
• Search infrastructure: Tune indices, analyzers, and embeddings; manage recall/precision trade-offs and de-duplication/near-duplicate suppression
• Cost & performance: Keep token usage, GPU/CPU time, and indexing costs under control with caching, pre-computation, and fallbacks
• Collaboration: Work closely with legal experts to turn user pain points into ranking features; document decisions and share clear playbooks

Qualifications

MINIMUM QUALIFICATIONS

• Strong hands-on experience improving search/retrieval systems (hybrid retrieval, reranking, or query understanding) in production
• Proven experience in building and deploying LLM-based products from prototyping to production
• Solid algorithms background (data structures, complexity, graph theory, statistics), IR/NLP intuition, and practical SQL skills
• Proficiency in TypeScript/Node.js (our core stack)
• Experience with one or more of: Azure AI Search, pgvector/PostgreSQL, OpenSearch/Elasticsearch, or similar
• Familiarity with modern embedding models and cross-encoders for reranking; ability to reason about latency, throughput, and quality trade-offs
• Ownership mindset, clear communication, and bias for action
• Proficiency in English
• Availability full-time. On-site in Zurich at least two days per week (hybrid)

PREFERRED QUALIFICATIONS

• You have a Swiss work permit or EU/EFTA citizenship
• Working proficiency in German (many sources are in German and we talk to German-speaking customers)
• Experience with evaluation pipelines (AI as judge, human-in-the-loop labeling, inter-annotator agreement, error analysis) applied pragmatically
• Practical knowledge of sparse methods (BM25+/BM25L/SPLADE), dense models (e5/BGE/ColBERT-style), and semantic re-ranking
• Experience deploying/operating small models or services (Docker; basic Kubernetes or serverless is a plus)
• Familiarity with our stack: Azure / NestJS / Next.js
• Knowledge and experience with legal systems, in particular Switzerland, Germany, USA 🧑‍⚖️

Benefits

• Direct impact: your ranking and retrieval changes immediately improve result quality and user trust
• Autonomy & ownership: Shape our legal research pipeline, across multi-faceted user intention understanding, dynamic retrieval and reranking
• Team: Work with a sharp, interdisciplinary team at the intersection of AI, search, and law.
• Compensation: CHF 8’000–12’000 per month + ESOP (employee stock options), depending on experience and skills