Employer description & source details
Lead the design and delivery of production-grade LLM applications, including embeddings, RAG pipelines, vector database integration, tool use, orchestration, and multi-agent patterns Lead the design of data pipelines, APIs, and enterprise integrations that embed AI/ML capabilities into business applications and collaboration platforms Partner with Product Owners, Data Scientists, AI Data Engineers, Platform Architects, Security, Risk and Compliance, and application teams to evaluate trade-offs and deliver cost-effective solutions aligned to enterprise standards Proven experience designing LLM-based applications, including RAG pipelines, embeddings, vector databases, tool integration, orchestration, prompt and context engineering, and model evaluation Deep experience with GenAI frameworks and ecosystems such as LangChain and Hugging Face Proven experience designing end-to-end MLOps capabilities using tools such as Vertex AI Pipelines, MLflow, or Kubeflow Advanced experience architecting cloud-native solutions on GCP; experience with AWS AI/ML services is a plus Proven experience deploying and operating scalable AI/ML services using Docker, Kubernetes, Terraform, CI/CD, observability, and incident-management practices Experience with event-driven workflows, enterprise data pipelines, and integrations such as Microsoft Teams and Microsoft Graph API Experience with multimodal AI solutions spanning text, image, and audio is preferred Proficiency in Microsoft Office Suite skills Maintain a continuous growth mindset through relationships with stakeholders, experts, colleagues, and mentors, as well as structured courses and programs
Extracted skills: python, aws, gcp, docker, kubernetes, terraform, security