omni:us

Data Scientist

• Design and build LLM-based agents and assistants for insurance workflows, including claims intake and triage, coverage checks, document and correspondence processing, fraud indicators and case summarisation
• Develop agentic workflows combining LLMs with tools, APIs, business rules and retrieval over policies, claim files and knowledge bases using RAG
• Implement multi-step reasoning and human-in-the-loop handover
• Apply and adapt multimodal models to extract information from complex insurance documents, including forms, invoices, reports, emails and images
• Build evaluation frameworks for generative and agentic systems, including test sets, automated and LLM-as-a-judge evaluation, accuracy and hallucination metrics, cost and latency tracking, and production monitoring
• Work on prompt and context engineering, and fine-tune or distill models for specific insurance tasks where beneficial
• Design guardrails for safe, explainable and auditable AI decisions aligned with GDPR and the EU AI Act
• Collaborate with product managers, engineers and insurance domain experts to bring solutions into production and measure business impact
• Assess developments in generative and agentic AI, new models and frameworks, and integrate useful technologies into products
• Document approaches, experiments and results for internal use and client communication

Explore Data Scientist at omni:us. Review requirements and application details.

Open roles

Data Scientist