GenAI Platform Engineer
Core
Building, operating, and scaling enterprise-grade Generative AI platforms and infrastructure to enable AI agents.
Role type
GenAI Platform Engineer
Builds
Enterprise-grade GenAI platforms, AI agents, and related infrastructure
Domain
Generative AI, Cloud Infrastructure, Enterprise Software
Deliverable
production ML models | infrastructure
Required skills
Python, Azure Cloud, Azure AI Services, RAG frameworks, Vector databases, REST APIs, DevOps, MLOps, Identity and Access Management, Observability
Preferred skills
Knowledge Graphs, CI/CD pipelines, Cloud cost optimization
Technologies
Azure OpenAI, Azure AI Search, Azure Functions, APIM, LangChain, LangGraph, LlamaIndex, pgvector, Chroma, Pinecone, Docker, Kubernetes, GitHub Actions, Azure DevOps, Terraform, Azure AD, OAuth2, RBAC, Microsoft Teams, ArgoCD, AWS Bedrock, Vertex AI
Responsibilities
Implement and maintain the LLM gateway; Develop internal SDK components for agents; Build and maintain RAG ingestion pipelines; Implement embeddings and vector store solutions; Develop Knowledge Graphs and enterprise adapters; Implement security controls for AI outputs; Configure agent sandboxing and identity integration; Set up observability frameworks; Implement resilience mechanisms; Develop evaluation benchmarks; Integrate CI/CD pipelines; Integrate platform components with enterprise tools; Manage cloud infrastructure and optimize LLM costs.
Seniority
Mid-level, hands-on IC
