- Design and develop Generative AI services and multi-agent systems
- Implement RAG, tool calling, and agent orchestration solutions
- Integrate and operate models through LLM gateways
- Develop LLMOps practices for monitoring, observability, and governance
- Implement consumption measurement, chargeback, and inference cost optimization mechanisms
- Build and maintain data pipelines for billing and metering
- Apply MLOps, CI/CD, automated testing, and model lifecycle management practices
- Respond to incidents and support monitoring, reliability, and continuous improvement of services
- Collaborate with global Product, Engineering, Platform, Security, and Data teams
Requirements
- Experience in Software Engineering and Applied AI
- Hands-on experience delivering GenAI projects in production environments
- Advanced English proficiency
- Knowledge of GenAI and Agentic AI
- Knowledge of multi-agent orchestration, tool calling, and multi-step reasoning
- Knowledge of RAG and prompt engineering
- Experience with LangChain, LangGraph, or equivalent frameworks
- Knowledge of LLMOps, LLM platforms, and LLM gateways such as LiteLLM or similar tools
- Experience integrating models through APIs
- Knowledge of observability and evaluation for LLM-based applications
- Experience optimizing latency and performance
- Knowledge of vector databases and retrieval mechanisms
- Advanced Python skills
- AWS experience preferred
- Understanding of best practices in architecture, observability, and reproducibility
- Knowledge of MLOps, version control, and experiment tracking
- Experience with CI/CD, automated testing, and deployment and rollback of AI services
- Knowledge of batch and streaming data pipelines
- Experience with Spark and Lakehouse architectures
- Knowledge of data orchestration
- Nice to have: Kafka and event streaming; Terraform and Infrastructure as Code; Databricks, including Delta Lake and DLT; internal developer platforms; experience working in global and distributed environments
Demonstrates expertise in Generative AI services, multi-agent systems, and LLMOps practices, with a strong focus on optimizing performance and implementing robust monitoring and governance mechanisms. Proficient in software engineering principles and experienced in delivering AI projects in production environments.
Highest-signal resume keywords
- Generative AI Services Development
- LLMOps Practices
- Multi-Agent Orchestration
- Advanced Python Skills
- CI/CD and Automated Testing
ATS Optimization Keywords
Hard Skills
- Software Engineering
- Applied AI
- GenAI Project Delivery
- RAG and Prompt Engineering
- API Integration
- Latency and Performance Optimization
- MLOps
- Data Pipeline Development
- Spark and Lakehouse Architectures
- Vector Databases
Soft Skills
- Collaboration
- Incident Response
- Continuous Improvement
Industry Keywords
- Observability
- Governance
- Chargeback
- Inference Cost Optimization
- Data Orchestration
- Batch and Streaming Data Pipelines
- Experiment Tracking
- Version Control
Tools & Technologies
- LangChain
- LangGraph
- LiteLLM
- AWS
- Kafka
- Terraform
- Databricks
- Delta Lake
- DLT
- Internal Developer Platforms
#J-18808-Ljbffr
AI Engineer – GenAI Platform, Mid-Level Arbeitgeber: Jobtailor
Als Front Office Supervisor in unserem dynamischen Team bieten wir Ihnen die Möglichkeit, in einem unterstützenden und freundlichen Arbeitsumfeld zu wachsen. Wir legen großen Wert auf die berufliche Entwicklung unserer Mitarbeiter und bieten regelmäßige Schulungen sowie die Chance, Verantwortung zu übernehmen. Unsere Lage ermöglicht es Ihnen, Teil einer lebendigen Gemeinschaft zu sein, während Sie gleichzeitig die Standards unseres Franchise-Partners einhalten und unseren Gästen einen unvergesslichen Aufenthalt bieten.
