{"lang":"en","work":[{"end":null,"role":"Full-Stack Engineer (AI Engineer)","depth":{"scope":null,"outcome":null,"rationale":null,"day_to_day":null,"constraints":null},"notes":null,"start":"2026-08","current":true,"summary":null,"highlights":["Enterprise-Scale Agentic Workflow: Addressed fragmented content planning, writing, review, approval, and publishing processes with long manual turnaround times by leading the design and implementation of an end-to-end Agentic Workflow for an organization of 160,000+ users. Orchestrated multi-stage agent workflows with Human-in-the-Loop compliance controls, reducing content production cycles from weeks to hours.","Production-Grade Agent Runtime and RAG: Addressed unstable reasoning, execution interruptions, unauthorized tool usage, and enterprise knowledge access constraints in long-running agent workflows by building a recoverable execution framework with LangGraph + PostgreSQL Checkpointing. Integrated dynamic Pydanticschemas,permission-awareTool-basedRAG,andprogressivecontextdisclosuretoreduceirrelevant context, improve multi-step reasoning stability, enforce controlled tool usage, and enable permission-based access to enterprise knowledge.","Production Engineering and Cloud Deployment: Reduced regression and deployment risks in rapid Agent system iterationbydeveloping1,000+pytestunit,integration,andregressiontestsandbuildingaDocker-basedCI/CDpipeline using GitHub Actions → AWS ECR → ECS Fargate. Integrated RDS PostgreSQL + Alembic for production data persistence, schema evolution, and database migrations."],"organization":"Mercedes-Benz Malaysia"},{"end":"2025-12","role":"Technical Consultant (AI & Automation Solutions)","depth":{"scope":null,"outcome":null,"rationale":null,"day_to_day":null,"constraints":null},"notes":null,"start":"2025-03","current":false,"summary":null,"highlights":["Multi-AgentOrchestrationandReasoning: Addressedlimitedreasoningstabilityandtaskdecompositionincomplex decision-support scenarios by independently building an end-to-end AI decision-support system with LangGraph and adopting the ReAct framework for autonomous multi-step problem solving. Developed a modular tool library for the supervisor agent to dynamically route tasks to specialized sub-agents, reducing hallucinations and achieving 95%+ accuracy across iterative prompt evaluations.","HybridRAGandRetrievalEnhancement: Addressedweakkeywordrecallandsemanticmatchingerrorsinenterprise knowledgeretrievalbybuildingahybridBM25+NeonpgvectorretrievalpipelinewithDashScopegte-rerankerfor second-stage reranking. Integrated SHA-256 deduplication and Ragas (LLM-as-a-Judge) evaluation to continuously optimize retrieval quality while processing 10,000+ data nodes per week.","Full-Stack Streaming and LLMOps: Improved real-time interaction and production observability for long-running agentreasoningworkflowsbyimplementingstreaminginferencewithFastAPI + Next.js + SSEandcontainerizingthe applicationwithDocker. DeployedservicesacrossVercel,Render,andCloudflareR2,whileintegratingLangSmith for end-to-end tracing, debugging, and Token cost analysis and optimization."],"organization":"Zhejiang Chamber of Commerce Malaysia"},{"end":"2023-12","role":"System Engineer","depth":{"scope":null,"outcome":null,"rationale":null,"day_to_day":null,"constraints":null},"notes":null,"start":"2023-03","current":false,"summary":null,"highlights":["NALA+ System Development: Contributedsignificantlytotheend-to-enddevelopmentoftheNALA+IoTgateway, covering requirement analysis, architectural design, core control logic, and production delivery. Managed cross-platform hardware driver adaptation and low-level protocol stack implementation, ensuring system stability in complex overseas industrial environments.","Communication Architecture & Optimization: Redesigned and implemented an asynchronous communication mechanism for distributed nodes to resolve network congestion and packet loss during high-concurrency sensor data ingestion. Conductedextensivestresstestingandperformancetuning,reducingsystemresponselatencybynearly30%.","JTC Project Implementation: Spearheaded energy simulation and energy-saving strategy iterations for Singapore JurongTownCorporation(JTC)officebuildings. OptimizedlightingcontrolalgorithmstoreduceLightingPowerDensity (LPD)to5W/m²,helpingtheprojectachievethehighestenergyefficiencystandardssetbytheBuildingandConstruction Authority (BCA)."],"organization":"Glorybene Smart Systems Pte. Ltd."}],"_meta":{"gaps":[{"kind":"missing_artifact","path":"projects[0].artifacts","severity":3},{"kind":"missing_rationale","path":"projects[0].depth.rationale","severity":3},{"kind":"missing_artifact","path":"projects[1].artifacts","severity":3},{"kind":"missing_rationale","path":"projects[1].depth.rationale","severity":3},{"kind":"missing_artifact","path":"projects[2].artifacts","severity":3},{"kind":"missing_rationale","path":"projects[2].depth.rationale","severity":3},{"kind":"missing_artifact","path":"projects[3].artifacts","severity":3},{"kind":"missing_rationale","path":"projects[3].depth.rationale","severity":3},{"kind":"unquantified","path":"work[0].depth.outcome","severity":2},{"kind":"unquantified","path":"work[1].depth.outcome","severity":2},{"kind":"unquantified","path":"work[2].depth.outcome","severity":2},{"kind":"thin_description","path":"projects[0].depth.outcome","severity":2},{"kind":"thin_description","path":"projects[1].depth.outcome","severity":2},{"kind":"thin_description","path":"projects[2].depth.outcome","severity":2},{"kind":"thin_description","path":"projects[3].depth.outcome","severity":2}],"source_confidence":0.0},"awards":[],"basics":{"name":"Fenyong Li","cover":null,"avatar":null,"intent":null,"summary":"A highly adaptable professional who consistently drives impact in any new environment. Ranked 1st in both my undergraduate and graduate cohorts, I secured top academic honors despite transitioning to a completely new major. Driven by a deep passion for real-world industry applications, I chose to decline a fully-funded U.S. Ph.D. offer and a Master’s admission to Nanyang Technological University.My core strengths lie in my quick learning ability, adaptability, and excellent teamwork, along with a strong willingness to learn and grow with others.","headline":null,"location":null,"profiles":[]},"skills":[],"projects":[{"end":null,"name":"Multimodal AR AI English Tutor","role":null,"tech":["Python","LangChain","RAG","LLM","VectorDB"],"depth":{"scope":null,"outcome":null,"rationale":null,"day_to_day":null,"constraints":null},"image":null,"notes":null,"start":"2026-05","summary":"Architected an autonomous multimodal AI tutoring agent, leveraging Augmented Reality to establish real-time visual perception and spatial awareness of the user’s physical environment. Engineered a cognitive decision-making core using GPT,incorporatingChain-of-Thought(CoT)promptingtodynamicallyanalyzeuserinteractionsandautonomouslyformulate personalized pedagogical strategies. Designed a multi-tier memory architecture (short-term dialogue buffering and long-term user profile retrieval) to maintain context continuity and adapt to the user’s evolving learning curve. Optimized the Python-Unityintegrationpipelinetoinstantlytranslatetheagent’slogicaldecisionsintosynchronized,multimodalexecutions, including fluid voice output and corresponding 3D avatar animations.","artifacts":[]},{"end":null,"name":"Generative VLM Evaluation & Reasoning","role":null,"tech":["PyTorch","HuggingFace","LLM","VLM"],"depth":{"scope":null,"outcome":null,"rationale":null,"day_to_day":null,"constraints":null},"image":null,"notes":null,"start":"2026-01","summary":"Spearheaded a comparative evaluation between a discriminative CNN-LSTM baseline and an advanced generative BLIP frameworktodeveloprobustperceptionlayersforclinicalAIassistants. LeveragedKaggle’shigh-performanceP100GPUsand theHuggingFaceTransformersecosystemtoorchestratecomplexmultimodaltrainingpipelines. Engineeredavisual-linguistic reasoning core using Vision Transformers (ViT) and Cross-Attention mechanisms. Successfully overcame the traditional ”classification trap” via auto-regressive token generation, significantly improving the agent’s semantic reasoning (F1 Score) and zero-shot Out-of-Vocabulary (OOV) capabilities.","artifacts":[]},{"end":null,"name":"Automated Farmland Management System","role":null,"tech":["Flask","Streamlit","MicroPython","IoT"],"depth":{"scope":null,"outcome":null,"rationale":null,"day_to_day":null,"constraints":null},"image":null,"notes":null,"start":"2024-06","summary":"Architected a full-stack ”Edge-Cloud” system for precision agriculture. Integrated CV-based facial authentication and millisecond-level fire warnings. Developed a sensor-driven intelligent ”Fertigation” system. Synergized UGV autonomous inspection with fixed stations for full-dimensional monitoring, achieving closed-loop management. Awarded ”Outstanding Graduation Project”.","artifacts":[]},{"end":null,"name":"Behavior Tree AI Agent Game Framework","role":null,"tech":["C#","Unity 3D","Client-Server State Sync"],"depth":{"scope":null,"outcome":null,"rationale":null,"day_to_day":null,"constraints":null},"image":null,"notes":null,"start":"2021-03","summary":"Designed a high-extensibility RPG core framework using Unity 3D. Developed a complex NPC Behavior Tree system and a dynamic quest-driven system to support flexible AI interactions and branching logic. Independently implemented a reliable Client-ServerStateSynchronization(StateSync)mechanismtoensuremulti-terminalconsistency. Optimizedsystemrobustness throughdecoupledinventoryandevent-drivenarchitectures. Recruitedasthefirstcorememberoftheuniversity’stop-tiertech society in recent years due to exceptional technical execution.","artifacts":[]}],"education":[{"end":"2024-06","field":"Computer Science and Technology","start":"2020-09","credential":"Bachelor of Science","institution":"Guilin University of Electronic Technology"},{"end":"2026-12","field":"Computer Science","start":"2025-03","credential":"Master","institution":"University of Malaya"}],"languages":[],"certifications":[],"contact":{"type":"resume4-relay","url":"https://fenyongli.resume4.ai/contact","method":"POST","note":"Messages are relayed to this person by ResumeForAI; no address is published. Automated senders need an employer key — see the docs URL. A form at the same URL is open to people without one.","docs":"https://resume4.ai/for-employers"}}