Jeevan Kumar

About

Built and shipped a production "Campaign AI" multi-agent system (LangGraph) that personalizes B2B outbound emails at scale using Apollo.io prospect data, clustering-based segmentation, and 21 persona variants. Notably uncovered that high click rates were largely email security scanners and created a validated bot-detection/scoring pipeline (timestamps/IP/user-agent/click patterns), bringing reported engagement down from ~40% to a trusted 5–8% that aligned with real conversions.

Key Strengths

• Built and deployed a production multi-agent LLM system for scalable B2B email personalization
• Designed persona-based targeting (21 persona variations) with clustering-driven segmentation
• Diagnosed inflated email click metrics and built bot-click detection to remove security-scanner noise
• Developed and validated a bot-scoring algorithm using timestamps, IPs, user agents, and click-sequence signals
• Outcome-driven validation: filtered metrics correlated better with replies/conversions (40% raw clicks to 5–8% human clicks)
• Robust agent/workflow design with step-level validation checks and independent agent testing
• Implemented confidence-based conditional routing and enrichment fallbacks to handle incomplete prospect data
• Pragmatic model/retrieval selection balancing cost, latency, and complexity; avoids overengineering
• Effective non-technical stakeholder communication via dashboards and clear metric reframing

Experience

Education

Skills

Languages

Certifications