Novartis Healthcare/BioTech

Senior AI Engineer

Basel, Switzerland +1 Hybrid Full-time

Location: Prague

Salary Range

Kč1,010,940.00 - Kč1,877,460.00

Job Description Summary

Location: Prague, Czech Republic

Working model: Hybrid

#LI-Hybrid

About the role

The Software & Workflows organization partners with scientists, data experts and AI specialists across Novartis Biomedical Research to transform scientific workflows and laboratory processes. Our ambition is to make advanced digital and AI capabilities usable, scalable and impactful, helping teams generate better insights, improve decisions and accelerate the discovery of innovative medicines.

As a Senior AI Engineer, you will own technical delivery on time-bound software initiatives within this portfolio, combining hands-on engineering with design ownership. You will design and deliver production-grade generative and agentic AI solutions that accelerate biomedical research, building scalable, secure LLM applications and agents on AWS.

This is a role for a curious, learning-oriented engineer who can navigate complexity, make thoughtful trade-offs and translate ambiguous problems into focused execution. You will work across engineering, science, architecture, operations and security, ensuring your solutions meet demanding standards for quality, performance, security, compliance and reliability.

What you will work on

You will work on agentic AI for drug discovery, scientific workflow automation and lab-in-the-loop systems. This may include end-to-end solutions such as multi-agent pipelines that accelerate target identification, agents that automate complex research workflows across teams, and lab-in-the-loop systems where AI supports experiment design, interpretation of results and the next iteration of research.

Your focus will be turning emerging agentic AI capabilities into reliable, secure and scalable tools that scientists can depend on.

Key responsibilities

  • Design and implement production-ready generative and agentic AI solutions on AWS, owning them from design through deployment and operation.
  • Build secure RAG solutions with hybrid search, embeddings, reranking, metadata and enterprise knowledge sources.
  • Develop intelligent agents using Amazon Bedrock AgentCore and agentic frameworks such as Strands, LangGraph, LangChain, CrewAI or a custom orchestration layer.
  • Implement multi-agent workflows, human-in-the-loop review, memory management, tool use and end-to-end traceability.
  • Design tool use and function calling so agents can connect securely to APIs, databases and enterprise systems, with MCP preferred where appropriate.
  • Create secure APIs and containerized backend services for models, agents, tools and conversational experiences.
  • Establish evaluation and observability practices, including test sets for agent behavior, LLM-as-judge or human review loops, tracing with tools such as CloudWatch, OpenTelemetry or LangSmith, and cost and latency monitoring.
  • Harden prototypes for production with security controls, guardrails, error handling and CI/CD using CDK or Terraform.
  • Build and maintain DevOps and MLOps pipelines, including containerized deployments, infrastructure as code, automated testing and model, data and prompt versioning for reproducibility.
  • Champion strong ML engineering practices, including rigorous evaluation, experiment tracking and reproducible pipelines.
  • Drive adoption of AI coding tools and provide technical leadership through reusable architectures, coding standards, design reviews and mentoring.
  • Additional Locations: Basel (City)

Job description provided by Novartis.
View the original posting