Senior GenAI / AI Platform Architect (LLM & RAG)

📍 Location: Dallas, TX (Hybrid – 3 days onsite)

Role Overview

We are looking for a Senior AI / GenAI Platform Architect to design and build enterprise Generative AI systems. The role focuses on developing LLM-based applications, RAG pipelines, and AI microservices deployed on cloud infrastructure with strong DevOps integration.

Key Responsibilities

• Design and implement LLM and Generative AI platforms

• Build RAG pipelines and vector search systems

• Develop AI microservices using Python (FastAPI / Flask)

• Implement multi-agent AI workflows and tool-calling frameworks

• Deploy AI systems using Docker, Kubernetes, and CI/CD pipelines

• Build LLM evaluation frameworks and AI safety guardrails

• Monitor AI performance, latency, and reliability in production

Required Skills

• Strong experience with Generative AI and LLM systems

• Hands-on with LangChain, LangGraph, or LlamaIndex

• Experience building RAG pipelines and embedding systems

• Strong Python development

• Experience with FastAPI or microservices architecture

• Cloud AI experience with AWS (Bedrock / SageMaker), Azure OpenAI, or Google Cloud Platform

• Knowledge of vector databases (Pinecone, FAISS, PGVector, Weaviate)

Preferred

• Experience building enterprise conversational AI systems

• Knowledge of AI safety, evaluation frameworks, and LLM monitoring

• Experience with Kafka, Neo4j, or distributed systems

Experience

• 7+ years software or ML engineering

• 3+ years working with GenAI / LLM platforms