Senior AI Engineer

Rivia is a data engine for clinical trial intelligence. It provides data infrastructure and AI-driven workflows for clinical trial teams, enabling biotechs to run studies more efficiently and to demonstrate which patients derive the greatest benefit from new therapies. Biopharma companies are the source of most therapeutic innovation, yet clinical development is frequently slowed by fragmented data and outdated tooling. Rivia delivers a real-time, integrated view across clinical trial data, improving both trial execution and the evaluation of new treatments.

Our goal is for Rivia to become the new standard infrastructure for modern drug development, bringing new therapies to market more successfully at a fraction of the cost.

About AI Engineering at Rivia

Given the highly complex nature of clinical trials and how they interface with our technology, the AI Engineering team at Rivia is pivotal in ensuring our clients achieve their desired outcomes and derive maximum value from our platform.

The team designs and operates agentic, production-grade AI workflows that power critical monitoring, data quality, and insight-generation capabilities for clinical trial stakeholders.

By building reliable, auditable, and scalable AI systems, AI Engineering helps transform fragmented clinical data into actionable intelligence and positions Rivia as the AI-first platform for clinical trial intelligence.

The Role

As a Senior AI Engineer at Rivia, you will architect and ship high-impact AI workflows that materially improve how clinical trial teams monitor studies, assess data quality, and make operational decisions.

You will work as a key technical contributor embedded in product initiatives, owning AI features end-to-end from design and evaluation through to deployment, observability, and continuous improvement.

The ideal candidate is a product-minded engineer who combines deep LLM and agentic systems expertise with strong software engineering skills, a bias to action, and a passion for turning cutting-edge AI into reliable, commercially impactful products in a complex, regulated domain.

Working Model: This role is based on-site in our Zürich office

What excites you

• Being part of a collaborative startup where you can make a direct impact on the product, the business, and the team.
• Working in a fast-paced environment where you can leverage your AI engineering expertise to solve complex, real-world problems in clinical trials.
• Building AI systems that customers rely on for critical decisions, where trust, traceability, and auditability are essential.
• Owning outcomes end-to-end, driving clarity, momentum, and quality without heavy oversight, and continuously learning and experimenting in the rapidly evolving LLM landscape.

Responsibilities

• Architect and ship production-grade agentic AI workflows, including tool use, orchestration, planning, memory, and structured outputs, for clinical trial intelligence use cases.
• Translate user workflows and product requirements into pragmatic, measurable AI solutions that work reliably in production and optimize for user and business value.
• Design and maintain evaluation pipelines, including gold sets, metrics, and experiments, and use them to drive iteration with rigor.
• Implement robust LLMOps practices, including tracing, monitoring, cost and latency management, safe deployment, and continuous improvement of AI systems in production.
• Design high-quality retrieval and context pipelines with strong guarantees on correctness, provenance, and auditability, particularly in regulated environments such as clinical trials.
• Collaborate closely with Engineering, Product, Design, Sales, and Customer teams to ensure AI features are usable, trusted, and commercially impactful.
• Stay deeply current with the LLM ecosystem, actively experiment with new models and tools, and translate innovation into practical product advantage.

What Excites us

• Product mindset, with a demonstrated ability to translate user workflows into pragmatic, measurable AI solutions that work reliably in production
• Deep familiarity with the current LLM ecosystem and active experimentation with new models, tools, and techniques.
• Proven…