Senior AI Engineer – Generative and Agentic AI

About the role

The Software & Workflows organization partners with scientists, data experts and AI specialists across Novartis Biomedical Research to turn scientific workflows and laboratory processes into advanced digital and AI capabilities. As a Senior AI Engineer in Prague, you will own technical delivery on time-bound software initiatives, combining hands-on engineering with design ownership. You will build production-grade generative and agentic AI solutions, including scalable, secure LLM applications and agents on AWS, working across engineering, science, architecture, operations and security.

Key responsibilities

• Design and implement production-ready generative and agentic AI solutions on AWS, from design through deployment and operation.
• Build secure RAG solutions with hybrid search, embeddings, reranking, metadata and enterprise knowledge sources.
• Develop intelligent agents with Amazon Bedrock AgentCore and 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.
• Create secure APIs and containerized backend services for models, agents, tools and conversational experiences.
• Set up evaluation and observability, including test sets, LLM-as-judge or human review loops, tracing (CloudWatch, OpenTelemetry, LangSmith) and cost/latency monitoring.
• Harden prototypes for production with security controls, guardrails, error handling and CI/CD using CDK or Terraform.
• Maintain DevOps and MLOps pipelines, including containerized deployments, infrastructure as code, automated testing and model, data and prompt versioning.
• Drive adoption of AI coding tools and provide technical leadership through reusable architectures, coding standards, design reviews and mentoring.

Required profile

• 5+ years of professional software engineering experience, including recent delivery of production-grade LLM and agentic AI solutions.
• Proven experience delivering generative AI, RAG and agentic AI solutions on AWS.
• Strong Python, API development, secure software engineering, testing and containerized services experience.
• DevOps and MLOps experience, including CI/CD, infrastructure as code (CDK or Terraform), containers and reproducible ML pipelines.
• Experience with Amazon Bedrock, agent orchestration, retrieval and grounding, and evaluation frameworks.
• Proficiency with at least one agent framework such as Strands, LangGraph, LlamaIndex, CrewAI or a custom framework.
• Good judgment in solution design and strong collaboration across engineering, science, architecture, operations and security teams.

Required skills

• Amazon Bedrock, AWS Lambda, Step Functions, ECS, EKS, API Gateway, DynamoDB, S3, IAM (desirable)
• Strands, LangGraph, LlamaIndex, CrewAI or similar agent frameworks
• Python, REST APIs, containerization, CI/CD, infrastructure as code

What we offer

• Annual base salary range of 1,010,940 to 1,877,460 CZK, with a possible performance-based bonus.
• Flexible and hybrid working options where possible.
• Minimum of 14 weeks of paid parental leave.
• Insurance plans, retirement plans, wellbeing resources and global recognition programs.