LLM / Agent Platforms
- A2A framework design
- Multi-hop reasoning agents
- RAG
- Vertex AI / Azure OpenAI
AI / Cloud / Distributed Systems
Lennon Lin
Staff-level Software Engineer / AI Platform & Cloud Architect
Building production LLM platforms, edge AI systems, and distributed data infrastructure from prototype to enterprise deployment.
Profile Focus
- A2A agent frameworks and multi-LLM routing
- RAG systems validated with FRAMES and Ragas
- Low-latency C++ inference on edge devices
- Spark / Hadoop telemetry pipelines at scale
About
Engineering leadership for intelligent systems.
I am a senior software engineer with 10+ years building production AI, computer-vision, and distributed systems end-to-end, from low-latency C++ edge inference engines to cloud-native LLM platforms.
My work sits at the intersection of AI platform architecture, RAG systems, edge-cloud deployment, and large-scale data pipelines on GCP and AWS, with repeated ownership from prototype through commercialized enterprise deployment.
Now · Updated Jun 2026
What I'm working on this month.
A monthly snapshot of my current career focus: production LLM systems, applied AI platform architecture, and the learning loops that keep my engineering judgment sharp.
Building
Production LLM platform capabilities at Acer — agent workflows, RAG systems, and LLM-assisted product QA automation
Shipping
Enterprise-ready AI workflows that move from architecture design to production deployment, with reliability, integration, and evaluation in mind
Exploring
How agentic testing, evaluation loops, and tool-use frameworks can raise software quality in complex product systems
Writing
Public-safe notes on AI platform architecture, LLM evaluation, and the engineering trade-offs behind production agent systems
Expertise
Systems experience across AI, cloud, and data.
Cloud Architecture
- GCP Cloud Run / Build / GCE
- AWS EC2 / S3 / IAM
- Docker
- Event-driven microservices
Distributed Data
- Spark
- Hadoop / MapReduce
- ETL pipelines
- Telemetry ingestion
Edge AI / Vision
- C++
- TensorRT / OpenVINO
- NVIDIA Jetson
- YOLO / SSD / FPN
Experience
A continuous arc from edge perception to LLM platforms.
Jan 2023 — Present
Associate Manager / Cloud Architect
Acer — Advanced Tech BU
Lead Architect for the cloud-native AI Agent Platform on GCP. Designed a modular Agent-to-Agent (A2A) framework with dynamic runtime loading, multi-agent orchestration, real-time ASR, and large-scale RAG retrieval.
- A2A framework + multi-LLM routing (GPT-4 Turbo / Claude 3.5 / Gemini 2.0)
- FRAMES + Ragas RAG validation across 3,131 human-verified QA pairs
- Led cross-functional teams (Backend, ML, ASR) and SI partners through enterprise rollouts
Jun 2019 — Jan 2023
Technical Lead & Cloud System Architect
Acer — Advanced Tech BU
Owned end-to-end engineering of a commercial edge-to-cloud AI platform deployed across retail and transportation. Built a real-time C++ inference engine with Cython/Python integration achieving sub-second latency in production.
- Co-led Taipei Metro Face-Recognition Gate proof of concept
- n:n face recognition platform — 97.24% MegaFace, 27 devices, 4,324 identities
- Distributed edge–cloud hybrid platform integrating embedded devices, CV sensors, and cloud microservices
Feb 2017 — Jun 2019
Deep Learning Tech Lead
Acer — Advanced Tech BU
Simulation-driven model development. Built a virtual-to-physical feedback loop pairing GTA-V environments with real-time shared-memory inference for autonomous-driving perception and control.
- ResNet-50 multi-task regression for steering-angle prediction
- Models deployed to golf carts and mini autonomous vehicles
- Segmentation, detection, and perception modules across the evaluation pipeline
Dec 2014 — Feb 2017
Distributed Systems Engineer
Acer — Advanced Tech BU
Built large-scale telemetry and UX analytics systems for global Acer devices. Re-architected daily preprocessing with Spark and Hadoop MapReduce, turning a 24-hour batch pipeline into a 2-hour distributed workflow.
- Global telemetry collection across 8 regional servers
- 300K–600K device packages ingested per day; about 50M–90M CSV rows processed daily
- Acer Software Innovation BU Excellence in Software Award (2015)
Independent Projects
Self-directed builds across AI tooling, cloud systems, mobile apps, and product experiments.
Independent product experiments that demonstrate end-to-end shipping, AI tooling, cloud/web deployment, and applied LLM workflows.
QuickPlayer
Google Play app · Shipped
A shipped Google Play music practice app and an experiment in AI-assisted product development, using LLMs to support feature ideation, UX flow design, specification writing, and implementation handoff.
Engineering focus
Mobile audio UXAI-assisted product planningApp-store shipping
Talking Amimal
AI voice prototype · Live demo
An AI voice interaction prototype for experimenting with TTS models, prompt-based speaking styles, accent variation, and character-like voice output.
Engineering focus
AI voice UXTTS evaluationPrompt-driven speechRapid prototyping
AI Translate
Browser extension · Shipped
A cross-browser extension for LLM-powered translation and language-learning assistance, turning selected web text into structured translation outputs and learning-friendly results.
Engineering focus
Chrome / Firefox extensionLLM integrationStructured AI outputLanguage-learning UX
LLM-Stock
Research prototype · Live demo
A personal research prototype for exploring LLM-assisted stock analysis, technical indicator summarization, sentiment signals, and decision-support dashboards.
Engineering focus
Financial data workflowsLLM summarizationSentiment signalsDashboard UX
Personal research prototype. Not financial advice.
Selected Work
Production systems with measurable impact.
01
AI Agent Platform
A2A framework / RAG / multi-LLM routing
Architected a cloud-native AI platform on GCP with dynamic runtime agent loading, multi-agent orchestration, and multi-LLM routing across GPT-4 Turbo, Claude 3.5 Sonnet, and Gemini 2.0 Flash.
- RAG knowledge base scaled to 2.4M Chinese characters
- FRAMES / Ragas validation with 3,131 human-verified QA pairs
- Hybrid deployment across RTX 4090 servers and cloud LLM APIs
02
Multilingual Technical Translation Agent
LLM workflow automation
Delivered a multilingual technical-translation agent with a four-stage verification pipeline covering exact match, AI review, generalization, and human review.
- 29 languages supported
- 99.9% accuracy on familiar specifications
- 120K rows processed in about 2 days across 10 API workers
03
Edge AI Face Recognition Platform
Commercial edge-to-cloud computer vision
Led architecture and engineering of a commercial n:n face-recognition platform with real-time C++ inference, edge hardware optimization, and cloud verification services.
- 97.24% MegaFace benchmark accuracy
- 27 production devices and 4,324 enrolled identities
- Sub-1-second recognition latency in real environments
04
Distributed Telemetry Platform
Spark / Hadoop analytics infrastructure
Re-architected global telemetry ingestion and preprocessing systems using Spark and Hadoop MapReduce for device analytics and OTA workflows.
- ETL runtime reduced from 24 hours to 2 hours
- 300K-600K device packages ingested per day
- About 50M-90M CSV rows processed daily
Career Highlights
Evidence of scale, ownership, and delivery.
10+ years in software engineering
Built AI products from prototype to commercial deployment
Validated RAG quality with 3,131 human-verified QA pairs
Delivered 29-language translation automation at 99.9% accuracy
Achieved 97.24% MegaFace accuracy for edge face recognition
Reduced ETL runtime from 24 hours to 2 hours
Processed about 50M-90M telemetry CSV rows per day
Contact
Currently at Acer building production LLM platforms. Open to deep technical conversations.
- Open to
- Staff / Principal IC roles in AI platform, applied ML infrastructure, LLM applications, and cloud architecture
- Peer conversations and engineering collaboration around AI platforms, edge-to-cloud systems, and LLM-integrated product architecture
- Best for
- Teams that need an experienced builder who can move from whiteboard architecture to running production within the same quarter.