Looking for a job

Nielzon Tolentino

@nielzontolentino

Lead AI Systems Engineer at Monee.ai who cut agent pipeline lag 99% and LLM spend 35% through production AI architecture.

Philippines

Message

At Monee.ai, I architected the event-driven Go backbone for an agent pipeline, cutting pipeline lag by 99% and memory use by 93%. I also optimized LLM serving and prompt caching, reducing LLM spend by 35% and per-request cost by 21%.

At Guerilla360, I built AI writing and clinical documentation products, including Interact and NavixScribeV2, and architected SmartFill, a multi-agent system for completing clinical EMR forms. These products cut documentation and form-completion time, while I also designed a no-code workflow automation engine and builder.

Experience

Work history, roles, and key accomplishments

Lead Software Engineer, AI

Monee.ai

Mar 2025 - Oct 2026 (1 year 7 months)

Architected the event-driven Go backbone of the agent pipeline, cutting pipeline lag 99% and memory 93%. Led LLM cost optimization and built the agent's LLM quality and safety layer, including RAG, evaluation harness, and guardrails.

Go DynamoDB Amazon SQS Lambda LLM Cost Optimization Prompt Caching Vector Search MLFlow Model Serving Observability Alerting RAG Harness GuardRails

Senior Full-Stack AI Engineer

Guerilla360

Jan 2024 - Mar 2025 (1 year 2 months)

Built Interact, a chart-grounded AI writing assistant, and led NavixScribeV2, an AI clinical documentation app. Architected SmartFill, a multi-agent AI system, and designed a no-code workflow automation engine.

React Azure OpenAI NodeJS Express Laravel Next.js Multi Agent Systems Workflow Automation Clinical Documentation

Full Stack Web Developer

Pythagoras Labs

Feb 2021 - Jan 2024 (2 years 11 months)

Delivered full-stack web applications and static websites for client businesses, translating requirements into working frontend interfaces and backend services. Consulted on SEO and social media strategy.

Fullstack Development Web Applications SEO Social Media Strategy