AI Systems Architect

📋 Description

• The router selects next role (executor/planner/verifier/clarifier) by task state and risk
• The context engine uses RAG pipelines, memory, MCP tools, and prompts with company knowledge
• Execution loop enables action-observe-act cycles for multi-step goals
• Verification layer defines checker design, confidence thresholds, and escalation for irreversible actions
• Eval loop provides feedback to improve the system without retraining

🎯 Requirements

• Deep understanding of LLM behavior, failure modes, and steering via prompts
• Experience shipping multi-step agentic systems in production
• Systems thinking to design interfaces, reason about failure modes, and scalable architecture
• Strong opinions on what works in LLM system design, backed by experience
• Comfort with ambiguity in a new field with no established playbooks

🎁 Benefits

• Experience with RAG architectures, vector DBs, and retrieval systems
• Familiarity with MCP, LangChain, LlamaIndex or similar agentic frameworks
• Background in distributed systems or backend infra
• Experience designing eval systems and benchmarks for LLM outputs