AI Solutions Architect
RemoteUnited States
Job Summary
Review current AI initiatives with engineering teams to identify consolidation opportunities and collaborate on a unified platform path. Design reference architectures for multi-agent orchestration, intent classification, and routing while defining context management strategies for token budgets and conversation summarization. Partner with data and ML teams to establish RAG architectures covering chunking, hybrid retrieval, and real-time serving, alongside prompt governance practices for versioning and monitoring. Define platform resiliency patterns for LLM-dependent systems including failover and cost controls, then establish AI safety standards for guardrails and hallucination mitigation. Collaborate with leadership to build a sequenced implementation roadmap for the platform buildout.
Required Qualifications
- 10+ years in software/ML architecture
- 5+ years in enterprise AI
- US time zone overlap
- Designed and shipped multi-agent AI platforms
- Built real-time conversational AI systems with proper session memory and context management
- Architected RAG pipelines that went beyond prototyping
- Worked across multiple LLM providers (OpenAI, Claude/Bedrock, Gemini, open-source)
- Designed intent classification systems that handle real-world complexity
- Built both real-time and batch ML pipelines
- Operated in cloud-native environments (AWS, GCP, or Azure)
Desired Qualifications
- Experience in retail, commerce, or customer service AI
- Hands-on with orchestration frameworks (LangGraph, LangChain, LlamaIndex)
- Experience with self-hosted model serving (Ollama, vLLM)
- Have been the person who wrote the AI platform standards that an engineering org of 50+ adopted
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.