AI Platform Architect

Position Title:

AI Platform Architect

Location:

Dallas, US (Onsite)

Basic Qualifications:

• 8 years in software architecture with strong focus on distributed systems
• Proficiency in Python, JavaScript
• Strong communication and architecture storytelling skills

Required Skills:

• Proven experience with LLMs, RAG architectures, and agentic systems (including agent harness and skill building)
• Deep understanding of agent orchestration, async/streaming patterns
• Strong hands-on expertise with Kubernetes and cloud-native/serverless architectures
• Experience designing AI platform components (gateways, observability, agent infrastructure)
• Experience with multi-agent frameworks (for example LangGraph, ADK) and emerging agent ecosystems
• Familiarity with LLMOps, evaluation frameworks, and AI governance
• Experience in GCP services such as BigQuery, Composer, Dataflow, Dataproc, Cloud function, Pub/Sub, and Cloud Storage
• Experience in implementation of security, governance, and compliance standards across GCP environments

Preferred Qualifications:

• Experience with enterprise-scale AI platform deployments

Role and responsibilities:

• Design end-to-end architectures for AI platforms leveraging RAG, agentic systems, and LLM-based applications
• Define and implement agentic patterns, including streaming, async workflows, multi-agent orchestration, and agent harness & skill development
• Architect platform components such as AI/LLM Gateways, agent frameworks, identity layers, and skill orchestration
• Build scalable solutions on Kubernetes and serverless cloud services
• Lead architecture across Amazon Web Services and/or Google Cloud Platform (GCP)
• Drive best practices for reliability, scalability, and performance of AI systems
• Translate complex AI capabilities into clear architectural narratives and business solutions

Job description:

Seeking experienced AI Platform Architect to design and lead next-generation AI systems built on LLMs and agentic frameworks. This role focuses on architecting scalable, production-grade AI platforms across cloud environments, with strong emphasis on RAG, agent orchestration, agent harness/skill building, observability, and gateway patterns.