Justin avatar

SPEAKING · ENGINEERING EXCHANGE

Speaking, engineering & contact

I translate frontier AI into architecture decisions, working systems, and engineering lessons teams can act on.

AI Platform & Agentic AI Engineer / Agent systems / RAG / Evaluation

Send an invitation Connect on LinkedIn

ENGINEERING PATH

Engineering background

My practical experience connects document intelligence, hybrid retrieval, agent orchestration, and platform governance. Each area links to verified projects or deep-dive notes.

  1. Enterprise Knowledge QA & Agentic RAG Pipeline

    Designed LangGraph state machines, rule-first deterministic routing, hybrid retrieval (BM25 + ChromaDB + RRF), and answer evaluation loops, converging to 98.0% weighted accuracy on a fixed 100-query benchmark.

    View Agentic RAG case study →

  2. Medical Receipt End-to-End OCR & Normalization Pipeline

    Built medical receipt OCR pipelines combining UVDoc rectification, YOLOv7 two-stage layout/table detection, PaddleOCR, and HospitalPipeline adapters to normalize 5+ hospital formats into unified JSON contracts.

    View OCR API project →

  3. Financial GenAI Platform Engineering & Governance

    Researched cloud-native AI runtimes, MCP tool governance, multi-agent orchestration, and operational handoff contracts, structuring the transition from PoC to an operable Agentic Operating System.

    Read Financial GenAI platform engineering →

PUBLIC SESSIONS

Selected talks

Public conference sessions backed by verifiable project implementations, evaluation benchmarks, and architecture articles.

  1. COSCUP

    GenAI Workflow: Building an Intelligent Technology Trend Insight System

    Open-source data pipelines, GenAI workflows, and interactive visualization for continuously tracking technology trends.

    Key takeaway: Learn how to build open-source data pipelines with GenAI workflows to turn fragmented information into interactive trend analysis.

    Explore the TrendScope implementation →
  2. iThome Cloud Summit Taiwan

    Generative AI Platform Engineering for Financial Services: Building a Scalable Agentic AI Hub

    Platform engineering, MCP integration, multi-agent infrastructure, realtime inference, and cloud governance.

    Key takeaway: Master the three-layer Cloud Native AI Runtime, MCP tool governance, and the three lifelines for financial AI deployment.

    Read the architecture article → Download slides (PDF) →
  3. iThome AI Enterprise Summit

    Financial-Grade Enterprise Agentic AI Architecture: From PoC to an Agentic Operating System

    Agentic RAG, multi-agent orchestration, self-verification, and LLM-as-a-Judge for high-stakes AI systems.

    Key takeaway: Gain actionable governance frameworks for Agentic RAG, multi-agent coordination, self-verification, and LLM-as-a-Judge.

    Read the governance article →

SPEAKING TOPICS

Topics I can speak about

Structured sessions tailored for engineering leadership, AI architects, and development teams.

  1. From Agent Demo to Agent System

    Orchestration, tools, memory, evaluation, observability, permissions, and safety boundaries.

    Audience: Engineering leadership, AI architects, senior backend engineers

    Key takeaway: Architectural patterns and evaluation frameworks to transform fragile agent demos into operable, traceable systems.

  2. RAG Beyond Retrieval: Enterprise Knowledge Architecture

    Knowledge architecture, hybrid search (Vector + BM25 + RRF), context validation, and self-retry.

    Audience: Teams deploying internal enterprise knowledge bases and unstructured doc Q&A

    Key takeaway: Production pipelines addressing synonyms, domain terms, tables, and hallucination containment.

  3. Financial-Grade AI Platform Engineering & Governance

    Cloud Native AI Runtime, MCP tool governance, LLM-as-a-Judge, and production handoff contracts.

    Audience: Decision-makers and platform engineers facing compliance, audit, and mission-critical requirements

    Key takeaway: Essential lifelines, audit trails, and control plane contracts required before shipping AI to enterprise production.

SPEAKER KIT

Speaker kit & media

Copyable bios, downloadable photo, and slides references for conference organizers and technical meetups.

Short bio (for event programs & announcements)

Justin is an AI Platform and Agentic AI Engineer focused on turning frontier AI into operable, measurable, and reliable enterprise systems. He brings hands-on delivery experience across agent state machines, enterprise RAG, Model Context Protocol (MCP) tooling, automated evaluation, and platform governance.

Full bio (for introductions & speaker profiles)

Justin is an AI Platform and Agentic AI Engineer who authors the Bloss0m technical publication. His engineering focus spans document intelligence, hybrid retrieval, agent state machine orchestration, automated evaluation, and enterprise platform governance. He has designed and delivered end-to-end medical receipt OCR normalization pipelines, controlled LangGraph Agentic RAG systems (achieving 98.0% weighted accuracy), and modular agent routing platforms. In technical sessions and architecture exchanges, Justin emphasizes honest trade-offs, real-world failure patterns, and verifiable engineering evidence, helping engineering teams and leadership transition frontier models into robust, operable, and observable production systems.
Download speaker photo (WebP) Credit: Justin (Bloss0m)

EDITORIAL METHOD

Editorial method

Bloss0m is an engineering publication: AI can assist the workflow, but evidence, interpretation, and publication decisions remain accountable to the author.

  1. Primary evidence first

    Technical claims are traced to papers, official documentation, specifications, repositories, or first-party announcements whenever possible.

  2. Synthesis over summary

    Each article must add architecture, trade-offs, limitations, experiments, or an actionable engineering decision beyond its sources.

  3. Transparent AI assistance

    AI may support research organization, drafting, localization, and visual ideation. The author verifies material claims, links, bilingual parity, and final editorial judgment.

  4. Living technical notes

    Substantive corrections and re-verification update the modified date. Durable guides are maintained as topic hubs rather than republished as artificial freshness.

CONTACT

Useful details for an invitation

When possible, include the audience, topic, format, location or online setup, and expected date. I welcome conferences, internal engineering sessions, podcasts, and architecture exchanges.

[email protected] LinkedIn GitHub
Speaking · Exchange

Bring frontier AI and engineering reality into the same conversation.

For speaking invitations or technical exchange, send the context directly by email or LinkedIn.

Send an invitation