Omnilex Tech Stack

AI-powered legal research platform for in-house counsel

Software Development Zurich 11–50 employees Partnership

Omnilex is an AI workspace purpose-built for legal teams, combining retrieval-augmented generation, LLM-powered search, and multi-model inference (Claude, ChatGPT, OpenAI) to accelerate legal research. The tech stack reveals a forward-looking architecture: pgvector + OpenSearch + Azure AI Search for semantic retrieval, Node.js/Next.js frontend, and active work on LLM agent runtimes in production. Current pain points—operational reliability of LLM workloads, messy legal-content ingestion across jurisdictions, and search relevance tuning—map directly to the project roadmap (retrieval ranking, enrichment pipelines, search infrastructure), suggesting a team focused on hardening AI reliability rather than feature breadth.

Tech Stack 30 technologies

Core StackReact Next.js TypeScript Jest Playwright Storybook Docker PostgreSQL Node.js Elasticsearch RAG Figma Mailchimp HubSpot Google Ads OpenAI Anthropic LinkedIn Ads CSS React Testing Library Azure Azure AI Search pgvector OpenSearch PostHog LinkedIn Claude ChatGPT Google Analytics 4 Perplexity

What Omnilex Is Building

◆Challenges

Scaling across europe
Messy web data extraction
Operational reliability of llm workloads
Complex buying processes
Messy multi-jurisdiction legal content
Reducing production surprises
Improving observability
Top ux pain points
Infrastructure reliability
Improving search relevance

▲Active Projects

Release golden path
Retrieval and ranking system
Llm-powered chatbot
Search infrastructure tuning
Product launches
Fix top ux pain points
Llm + agent runtime in production
Migration workflows
Establish component library baseline
Build enrichment pipelines for tagging, classification, summarization, embeddings, entity extraction, and graph relationships

Hiring Activity

Accelerating30 roles · 25 in 30d

Department

Engineering

Sales

Data

Marketing

Design

Legal

Seniority

Mid

Senior

Lead

Company intelligence

Find more companies like Omnilex by tech stack, pain points and active projects

Get started free

About Omnilex

Omnilex builds an AI workspace for law firms and in-house legal teams, replacing manual legal research with AI-assisted workflows. The platform ingests legal documents across multiple jurisdictions, applies semantic search and entity extraction, and surfaces insights through LLM-powered chat and retrieval. Based in Zurich with 11–50 employees, Omnilex is actively hiring across Switzerland, Germany, and Austria, with a hiring velocity that has accelerated over the past month. The team is split engineering-heavy (12 eng, 3 data, 3 marketing), reflecting a technical product still in active optimization rather than a sales-driven phase.

HeadquartersZurich

Company Size11–50 employees

Hiring MarketsSwitzerland, Germany, Austria

Frequently Asked Questions

What tech stack does Omnilex use?

React, Next.js, TypeScript, PostgreSQL, Azure, Node.js, and a vector-search layer (pgvector, OpenSearch, Elasticsearch, Azure AI Search). LLM integrations span Claude, ChatGPT, and OpenAI. Frontend testing via Jest, Playwright, and Storybook.

What is Omnilex working on?

Retrieval ranking and search infrastructure tuning, LLM agent runtimes in production, enrichment pipelines (tagging, classification, embeddings, entity extraction), UX improvements, and a product launch roadmap. Core focus is operational reliability of LLM workloads and multi-jurisdiction legal content handling.