Founding Software Engineer — Oct 2025 to Feb 2026

Franklink

Architected the multi-agent brain behind the world's first AI-native professional network — iMessage-based orchestration with persisted memory, selective dispatch across 5 sub-agents, and a Kafka-backed event pipeline sustaining 50+ concurrent sessions.

Multi-Agent Systems Kafka AWS ECS Agentic RAG

From Zero to One

As the Founding Software Engineer, I owned the complete lifecycle of the Franklink platform: from initial architecture to production deployment on AWS ECS. I designed an iMessage-based multi-agent orchestration layer with persisted memory, selective dispatch across 5 sub-agents (onboarding, networking, group chat networking, group chat maintenance, profile updates), and agentic RAG over 8 permissioned tools (database, email, calendar, profile, networking, group chat, conversation sync, email extraction).

The conductor agent (InteractionAgent) analyzes incoming messages and routes to specialized ExecutionAgents via a ReAct loop. Each agent accesses enriched user context pulled from Supabase profiles and a Zep knowledge graph storing conversation history and email activity analysis.

I engineered a Kafka-backed event pipeline with at-least-once delivery, idempotency keys stored in Redis (24h TTL), and a 3-tier retry strategy (30s, 2m, 10m) with dead letter queue after 6 attempts. The system sustained 50+ concurrent sessions with p99 latency within 40% of single-session baseline, using keyed concurrency and 1.5s message coalescing.

Technical Highlights

  • 5 Sub-Agent Orchestration

    An InteractionAgent conductor selectively dispatches to 5 specialized ExecutionAgents via ReAct loops, each with dedicated tools and persisted memory through Zep knowledge graphs and Supabase.

  • Kafka Event Pipeline

    At-least-once delivery with idempotency keys in Redis, 3-tier retry (30s/2m/10m) with DLQ after 6 attempts. Keyed concurrency and partition flow control sustain 50+ concurrent sessions with p99 latency within 40% of single-session baseline.

  • 8 Permissioned Tools

    Agentic RAG over database, email, calendar, profile management, networking, group chat, conversation sync, and email extraction. Tools receive enriched context from Zep facts and Supabase profiles.

Under The Hood

Orchestration Engine

A stateless task-based design: the InteractionAgent (conductor) classifies intent and dispatches to specialized ExecutionAgents via Task definitions. No checkpoint serialization overhead — memory lives in Zep and Supabase. Message coalescing with a 1.5s debounce window prevents redundant agent invocations.

Persisted Memory

Three-tier memory: ExecutionMemory (per-task scratchpad), InteractionMemory (cross-task state), and TaskHistorySaver (persistent logs). Zep knowledge graph stores enriched user facts from conversation history and email activity analysis for long-term context.

Cloud Infrastructure

Docker Compose orchestrates Kafka, workers, and the ingest service. The Kafka pipeline uses 5 topics (inbound, 3 retry tiers, DLQ) with 12 partitions and 3x replication. Deployed on AWS ECS with IAM authentication for MSK.

See It In Action

Walk through the full Franklink experience — from your first message to building a professional network, all through iMessage.

  View Product Demo