Job Summary
We are seeking a Senior Generative AI Platform Engineer to build scalable enterprise AI platforms leveraging modern LLMs, AI orchestration frameworks, cloud-native technologies, and Model Context Protocol (MCP). The ideal candidate should have strong experience building production-grade GenAI applications and AI developer platforms.
Key Responsibilities
- Design enterprise-grade Generative AI platforms.
- Build AI applications using OpenAI, Claude, Gemini, and Llama models.
- Develop AI workflows using LangGraph, LangChain, and LlamaIndex.
- Implement Model Context Protocol (MCP) integrations.
- Build scalable RAG pipelines using vector databases.
- Develop REST APIs and FastAPI services.
- Deploy AI workloads on Azure AI Foundry or Amazon Bedrock.
- Implement AI monitoring, logging, and observability.
- Collaborate with platform engineering and DevOps teams.
- Follow Responsible AI and AI Governance standards.
Required Skills
- Python
- Generative AI
- LLMs
- LangGraph
- LangChain
- LlamaIndex
- MCP (Model Context Protocol)
- Prompt Engineering
- RAG
- FastAPI
- REST APIs
- OpenAI
- Anthropic Claude
- Google Gemini
- Azure AI Foundry
- Amazon Bedrock
- Docker
- Kubernetes
- GitHub Actions
- CI/CD
Preferred Skills
- CrewAI
- Semantic Kernel
- AI Guardrails
- LangSmith
- OpenTelemetry
- AI Security
Rate:
Not specified
Location:
Kansas City
IR35 Status:
Outside
Remote Status:
Remote
Industry:
AI & Machine Learning
Seniority Level:
Senior