3 days ago
Prague, CzechiaStaff+
Responsibilities
- Own the architecture, design, development, deployment, monitoring, reliability, and continuous improvement of agentic AI platforms and solutions.
- Transform scientific workflows, drug discovery processes, and lab-in-the-loop systems into scalable agentic AI-enabled capabilities.
- Make architecture decisions for agentic systems and large language model inference at scale on AWS, including Amazon Bedrock and AgentCore.
- Establish reference architectures and engineering practices for performance, scalability, security, governance, and maintainability.
- Define and advance DevOps, MLOps, and AgentOps standards covering infrastructure as code, containers, reproducible pipelines, versioning, experiment tracking, evaluation, and observability.
- Guide the evaluation, integration, and optimization of AI models, agent orchestration frameworks, and platform components.
- Partner with product, data, architecture, security, scientific, and business stakeholders on technical roadmaps and priorities.
- Provide technical leadership through design reviews, coding standards, mentorship, and architectural direction without direct people management.
Requirements
- 8+ years of professional software and/or AI engineering experience, including production-grade AI delivery and hands-on technical leadership.
- Deep hands-on experience building AI agents on AWS using Amazon Bedrock, including models, Agents, Knowledge Bases, Guardrails, and Bedrock AgentCore.
- Proficiency with at least one agent framework such as Strands, LangGraph, LlamaIndex, CrewAI, or custom orchestration.
- Strong Python expertise and experience with AWS services such as Lambda, Step Functions, ECS/EKS, API Gateway, DynamoDB, S3, and IAM.
- Experience with retrieval-augmented generation, chunking, embeddings, vector stores such as OpenSearch or pgvector, and tool use or function calling.
- Deep DevOps and MLOps expertise, including CI/CD, infrastructure as code with CDK or Terraform, containers, orchestration, reproducible pipelines, AI evaluation, and observability.
- Ability to translate ambiguous business or scientific problems into secure, resilient production solutions with guardrails, error handling, and governance.
- Ability to set technical direction, make design decisions, and communicate complex trade-offs to technical, scientific, product, and business stakeholders.
- Preferred experience with AI coding tools, AgentOps, AI governance and compliance in regulated or life-sciences environments, and awareness of the EU AI Act.
- Preferred Model Context Protocol experience.
Benefits
- Annual base salary range of 1,354,220 CZK to 2,514,980 CZK, with potential performance-based bonus.
- Insurance plans, retirement plans, wellbeing resources, and global recognition programs.
- Flexible and hybrid working options where possible; the role is located in Prague, Czech Republic or Basel, Switzerland.
- Minimum of 14 weeks of paid parental leave.
- Benefits and compensation vary by country and applicable local legal requirements.
About Novartis
Novartis is an innovative medicines company. Every day, working to reimagine medicine to improve and extend people’s lives so that patients, healthcare professionals and societies are empowered in the face of serious disease. Our medicines reach more than 250 million people worldwide. Find out more at https://www.novartis.com See our community guidelines: https://go.novartis.social/3Nboxki