2 days ago
Basel, SwitzerlandStaff+
Responsibilities
- Own the end-to-end architecture, design, development, deployment, monitoring, reliability, and continuous improvement of agentic AI platforms and solutions.
- Take ambiguous business and scientific workflow problems through to hardened, scalable production solutions.
- Design agentic systems and LLM inference at scale on AWS, including Amazon Bedrock and AgentCore, while balancing reliability, latency, cost, security, and governance.
- Establish engineering best practices and reference architectures for AI performance, scalability, security, governance, and maintainability.
- Define DevOps, MLOps, and AgentOps standards covering CI/CD, infrastructure as code, containerization, reproducible pipelines, versioning, and experiment tracking.
- Guide the evaluation, integration, and optimization of AI models and orchestration frameworks.
- Define evaluation and observability standards, including agent test sets, LLM-as-judge or human-review loops, tracing, and cost and latency monitoring.
- Partner with product, data, architecture, security, and business stakeholders on technical roadmaps, platform standards, and priorities.
- Lead through technical influence via design reviews, coding standards, technical mentorship, and cross-functional technical decision-making.
Requirements
- 8+ years of professional software or AI engineering experience, including shipping production-grade AI solutions and serving as a hands-on technical lead.
- Deep hands-on experience building AI agents on AWS, including Amazon Bedrock models, Agents, Knowledge Bases, Guardrails, and Bedrock AgentCore capabilities.
- Proficiency with at least one agent framework such as Strands, LangGraph, LlamaIndex, CrewAI, or a custom orchestration framework.
- Strong Python expertise and experience with AWS services including Lambda, Step Functions, ECS/EKS, API Gateway, DynamoDB, S3, and IAM.
- Experience with RAG, chunking, embeddings, vector stores such as OpenSearch or pgvector, and tool-use or function calling connecting agents to APIs, databases, and enterprise systems.
- Deep DevOps and MLOps expertise, including CI/CD, infrastructure as code with CDK or Terraform, containers and orchestration, reproducible pipelines, ML evaluation, and observability.
- Ability to incorporate security, guardrails, and robust error handling into production solutions and communicate technical trade-offs clearly.
- Experience setting technical standards and direction across engineering teams.
- Experience operationalizing AI coding tools across engineering teams and working with vendors or external engineering partners is desirable.
- Experience with AI governance and compliance in regulated or life-sciences environments, including awareness of the EU AI Act, is desirable.
- MCP experience is preferred.
Benefits
- Flexible and hybrid working options where possible; the posting is marked hybrid and lists Basel, Switzerland, and Prague, Czech Republic locations.
- Insurance plans, retirement plans, wellbeing resources, and global recognition programs.
- Minimum 14 weeks of paid parental leave.
- Potential eligibility for a performance-based bonus, with details provided during the application process.
Categories
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
