$ whoami

Dongjin Kim

AI & ML Engineer — MLOps, LLM pipelines, full-stack ML applications.
M.S. Computer Science (AI), Georgia Tech · CKA-certified · previously DevOps at Hyundai infotainment platform (Kubernetes across 20+ nodes).
Toronto, ON.

CKA CertifiedTF Developer CertM.S. CS — Georgia TechToronto, ON · PR

Technical Skills

Languages

PythonC++JavaScriptBashMATLAB

ML & Perception

PyTorchTensorFlowscikit-learnOpenCVYOLOv8MediaPipefaster-whisper

Systems & Backend

FastAPIWebSocketasyncioSQLiteDockerKubernetes (CKA)JenkinsGit

AI & APIs

OpenAI APIClaude APILLM Tool-useNLP PipelinesData Visualization

Cloud & Infra

AzureGrafanaPrometheusInfluxDBCloudflare Zero Trust

Certifications

Certified Kubernetes Administrator (CKA)
TensorFlow Developer Certificate

Projects

8 live applications · 2 coursework

End-to-end systems across investment operations, medical AI, agents, and reinforcement learning — every live project runs in production.

ops.djkimlab.com
Investment Ops
Investment OpsLive

Investment Operations Suite

Live back-office platform — five operations modules, one market simulation.

5 ops modules · 1 live market sim

A live back-office platform — five operations modules over one continuously evolving market simulation: custodian reconciliation and break detection, NAV and performance reporting, multi-source data quality monitoring, trade-confirmation extraction with an SOP assistant, and trade-to-ledger double-entry accounting. Anchored to real FRED market data.

PythonFastAPIInvestment OperationsLive SimulationFREDNext.js
ops.djkimlab.comRead more →
radiology.djkimlab.com
Medical AI
Medical AILive

Radiology AI

Chest X-ray triage, explainability and semantic search — one shared model.

14 conditions · 112k X-rays · 3 workflows on 1 model

A chest X-ray analysis platform over the NIH ChestX-ray14 corpus — DenseNet121 multi-label triage with FHIR patient context, Class Activation Map explainability showing which regions drove each prediction, and CLIP ViT-B/32 semantic image search. One shared model, three workflows.

PyTorchDenseNet121CLIPGrad-CAMFHIRNext.js
radiology.djkimlab.comRead more →
rl.djkimlab.com
Reinforcement Learning
Reinforcement LearningLive

Reinforcement Learning Lab

A DQN agent and a Connect-4 game-AI arena in one workbench.

3 search algorithms · play live in browser

Two reinforcement-learning workbenches in one — a DQN agent learning Gymnasium control tasks (CartPole, Acrobot) with reward and loss streamed live over WebSocket, and a Connect-4 arena pitting alpha-beta minimax, Monte Carlo Tree Search, and an AlphaZero-style self-play network against you.

PyTorchDQNMCTSAlphaZeroGymnasiumNext.js
rl.djkimlab.comRead more →
agent.djkimlab.com
Agentic AI
Agentic AILive

Autonomous AI Agent

A tool-using agent that plans, acts, observes and self-corrects.

AST-sandboxed Python · self-corrects · streamed trace

A tool-using reasoning agent that runs a plan → act → observe loop — calling tools, reading results, and self-correcting until it solves the task. Tools include a safe calculator and a restricted Python sandbox (AST-validated, no file or network access). The full reasoning trace is streamed live.

LLMAgentic AITool UseSandboxFastAPINext.js
agent.djkimlab.comRead more →
audio.djkimlab.com
NLP & Speech
NLP & SpeechLive

Audio Intelligence

Speech → transcription, sentiment, keywords — a full NLP pipeline.

Speech → 4 structured outputs in one pass

Upload audio → Whisper tiny transcription with timestamps, sentence-level sentiment via DistilBERT, keyword extraction, and speaking rate. Full NLP pipeline from raw speech to structured analysis report.

faster-whisperDistilBERTNLPSentimentFastAPINext.js
audio.djkimlab.comRead more →
lamp.djkimlab.com
Vision & HCI
Vision & HCILive

Responsive Lamp

A gaze-tracked virtual desk lamp with object detection and memory.

6-DOF lamp · real-time gaze + object memory

6-DOF virtual desk lamp with real-time gaze tracking via MediaPipe iris landmarks, YOLOv8 object detection, and spatial memory queries answered by GPT-4o-mini grounded in a local visual store.

MediaPipeYOLOv8Three.jsGPT-4o-miniWebSocketFastAPI
lamp.djkimlab.comRead more →
quant.djkimlab.com
Quant Finance
Quant FinanceLive

Quant Trading Platform

Regime-aware swing trading with multifactor ranking and paper execution.

Multifactor + HMM regime · 15-min paper-trade cycle

Regime-aware swing trading platform for US equities and ETFs. Multifactor ranking model (trend, momentum, relative strength, accumulation/volume) layered with HMM-based market regime detection, FinBERT sentiment analysis, and FRED macro inputs. Paper trading engine with entry sizing, stop/TP/trailing-stop, and a 15-min scheduled cycle.

PythonFastAPIHMMFinBERTFREDIBKRTimescaleDBStreamlit
quant.djkimlab.comRead more →
chatbot.djkimlab.com
LLM & RAG
LLM & RAGLive

Consulate Chatbot

A grounded RAG chatbot for the Korean Consulate in Toronto.

216 official posts · BM25 + embeddings hybrid

RAG-based civil service chatbot for the Consulate General of Korea in Toronto. Hybrid BM25 + OpenAI embedding search over 216 official bulletin posts (passport, visa, notarization, military service, and more), answered by GPT-4o grounded strictly in official content — with source links and disclaimer.

PythonFastAPIOpenAIRAGBM25SSE
chatbot.djkimlab.comRead more →
coursework · Georgia Tech
Coursework
CourseworkGeorgia Tech

Deep Learning — CS 7643

CNNs, RNNs and attention implemented from scratch in PyTorch.

Implemented CNNs, RNNs, and attention mechanisms from scratch in PyTorch for image classification, sequence modelling, and transfer learning. Reproduced foundational architectures and benchmarked against pretrained baselines.

PyTorchCNNRNNAttentionTransfer Learning
case studyRead more →
coursework · Georgia Tech
Coursework
CourseworkGeorgia Tech

ML for Trading — CS 7646

A market simulation framework with Q-learning strategy learners.

Built a full market simulation framework implementing Q-learning and random forest strategy learners. Evaluated portfolio performance using Sharpe ratio, cumulative return, and drawdown against buy-and-hold baselines.

PythonQ-LearningRandom ForestSharpe RatioRL
case studyRead more →

Experience

Dec 2025 — Present

Toronto, ON

Administrative Officer — Technical Systems

Consulate General of the Republic of Korea

Political and Economic Affairs

PythonLLM APIsNLPFastAPITelegram BotCloudflare Zero Trust
  • Designed and deployed a Python backend pipeline ingesting ~15 live government/media sources, classifying articles by NLP topic, and generating structured summaries via LLM APIs — runs up to 5×/day with automated monitoring, error logging, and retry logic.
  • Built a searchable internal web dashboard consolidating stakeholder profiles, company activity, and archived briefings into a single queryable store.
  • Replaced a 2.5-hour manual briefing process with a 20-minute review workflow; automated daily digest distribution via Telegram bot; secured access with Cloudflare Zero Trust.

Feb 2022 — Dec 2022

Seongnam, South Korea

DevOps Engineer

Luxoft

Hyundai Motors — Infotainment Platform

KubernetesJenkinsDockerGrafanaPrometheusAzureBash
  • Owned the CI/CD pipeline for a large-scale vehicle infotainment platform: Jenkins builds, Maven dependency resolution, Docker image builds, and deployments to Kubernetes clusters spanning 20+ physical and cloud nodes.
  • Designed 10+ Grafana dashboards for build and deployment monitoring; implemented Bash-based alerting integrated with Azure Power Automate.
  • Made an architecture decision that averted a critical misconfiguration on a 128 GB production server.

Mar 2021 — Jul 2021

Suwon, South Korea

Software Application Engineer

CSI Vision

MATLABHDF53D ReconstructionSignal ProcessingInterpolation
  • Designed a MATLAB algorithm to reconstruct 3D molecular structures from 2D cross-sectional HDF5 measurement data for the Korea Institute of Materials Science ($20K contract).
  • Developed interpolation and gap-filling tools to handle missing measurements; validated reconstruction fidelity against reference models and presented progress weekly to client stakeholders.

Education

May 2026

Georgia Institute of Technology

M.S. in Computer Science — Artificial Intelligence specialization

2022

Korea National Open University

B.S. in Computer Science

2017

Kyung Hee University

B.B.A. in Business Administration

$ status --open-to-work

Currently open to

  • ML / AI Engineer roles — production systems, LLM pipelines, applied research engineering.
  • MLOps / AI Infrastructure roles — CKA-certified, comfortable owning the path from train run to serving.
  • Consulting on shipping working AI systems on a small-team budget.
  • Based in Toronto, ON (PR) — remote · hybrid · relocation all on the table.