3 days ago
Prague, Czechia or Basel, SwitzerlandSenior
Responsibilities
- Design, implement, deploy, and operate production-ready generative and agentic AI solutions on AWS.
- Build secure RAG solutions using hybrid search, embeddings, reranking, metadata, and enterprise knowledge sources.
- Develop intelligent agents and multi-agent workflows with memory management, tool use, function calling, human review, and traceability.
- Create secure APIs and containerized backend services for models, agents, tools, and conversational experiences.
- Establish evaluation, testing, tracing, observability, cost-monitoring, and latency-monitoring practices for agent behavior.
- Productionize prototypes with security controls, guardrails, error handling, infrastructure as code, and CI/CD.
- Build and maintain DevOps and MLOps pipelines with containerized deployments, automated testing, and model, data, and prompt versioning.
- Champion ML engineering practices and provide technical leadership through reusable architectures, coding standards, design reviews, and mentoring.
Requirements
- 5+ years of professional software engineering experience, including recent hands-on delivery of production-grade LLM and agentic AI solutions.
- Proven experience designing and delivering generative AI, RAG, and agentic AI solutions on AWS.
- Strong Python, API development, secure software engineering, testing, and containerized services experience.
- Solid DevOps and MLOps experience, including CI/CD, infrastructure as code such as CDK or Terraform, containers, and reproducible ML pipelines.
- Hands-on 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 solution-design judgment, including knowing when a simple workflow is more appropriate than a multi-agent design.
- Strong collaboration and communication skills across engineering, scientific, architecture, operations, and security teams.
- Experience with Bedrock AgentCore, including agent runtime, memory, tool access, and identity, is desirable.
- Experience with MCP clients and servers and AWS services such as Lambda, Step Functions, ECS, EKS, API Gateway, DynamoDB, S3, and IAM is desirable.
- Experience in a regulated or life-science environment, AI coding assistants, and responsible AI practices is desirable.
- The posting also lists Code Analysis, Hardware Architectures, Microsoft .NET Platform, MVVM, MySQL, NoSQL Databases, OOD, RTOS, REST, Software Architectures, Software Design, Software Documentation, Structured Programming, Systems Architecture, Ubuntu, Unit Testing, and Windows Presentation Foundation as desired skills.
Benefits
- Hybrid working model in Prague, Czech Republic.
- Competitive benefits including insurance plans, retirement plans, wellbeing resources, and global recognition programs.
- Flexible and hybrid working options where possible.
- Minimum of 14 weeks of paid parental leave.
- Potential eligibility for a performance-based bonus; benefits and compensation vary by country and 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