{ "identity": { "name": "Sebastian Torres Ortiz", "headline": "Machine Learning Engineer · Computer Vision · AI Agent Systems", "location": "Bogotá, Colombia", "yearsOfExperience": "7+", "education": "Systems Engineering · Universidad Nacional de Colombia", "summary": "Machine learning engineer with 7+ years building software, who takes models from data to production. He trains computer-vision models, serves them fast and cheap, and builds the AI agents and data platforms around them. Recently: rebuilt a retail vision inference service (24× faster, 82% cheaper), trained six vision models (up to 96.7% accuracy), and built AI agents that have handled 812k+ messages.", "availability": "Open to machine learning, computer vision and AI-agent roles, contracts and collaborations.", "contact": { "emails": [ "admin@risksvision.xyz", "sebastianto1999@gmail.com" ], "preferred": "Email admin@risksvision.xyz with a short note about the system you want to build.", "cv": "/sebastian-torres-portfolio.pdf", "photo": "/images/sebastian.jpg", "linkedin": "https://www.linkedin.com/in/sebastian-torres-ortiz/", "websites": [ "https://risksvision.xyz", "https://realslab.xyz" ] } }, "headlineMetrics": [ "24× faster inference — Shelf photo end-to-end: 17 s → 0.7 s after the GPU migration.", "−82% serving cost — Inference service rewritten in Rust + ONNX Runtime: $66.70 → $13.71 / month.", "96.7% SKU accuracy — Product classifier measured on 31,311 unseen photos.", "0 errors / 8,833 runs — Seven days of production traffic, all served on GPU." ], "experience": [ { "role": "ML & AI Agentic Systems Lead", "scope": "computer vision & AI agents", "when": "2025 – now", "result": "24× faster inference · 812k+ agent messages", "href": "#ml-production", "projectIds": [ "production-vision", "vision-models", "ai-agents", "retail-census" ] }, { "role": "Founder", "scope": "Reals Lab · real-estate intelligence", "when": "2026", "result": "18.5k listings monitored · 97.8% best audit ROC-AUC", "href": "#real-estate-avm", "projectIds": [ "reals-lab-valuation", "reals-lab-audit" ] }, { "role": "Founder", "scope": "Risks Vision · ML strategies run by AI agents", "when": "2025 – 2026", "result": "102 strategies tested · 33% CAGR backtest", "href": "#quant-trading-ml", "projectIds": [ "risks-vision" ] }, { "role": "Data systems", "scope": "geospatial retail census", "when": "2025 – now", "result": "~70k stores · 666 isochrones", "href": "#retail-census", "projectIds": [ "retail-census" ] }, { "role": "Software engineer → DevOps tech lead", "scope": "Unreal Destiny · blockchain RPG", "when": "2021 – 2024", "result": "100k+ on-chain transactions · Go & Solidity", "href": "#bbstudios", "projectIds": [ "unreal-destiny" ] } ], "earlierExperience": [ { "role": "Senior developer", "company": "Global Hitss", "when": "2020 – 2022" }, { "role": "Creative director", "company": "Natural Simulators", "when": "2020 – 2021" }, { "role": "Web developer", "company": "ESinergia", "when": "2020" }, { "role": "Web developer", "company": "InkCode Corp", "when": "2019" } ], "skills": [ { "name": "Data", "proof": "~70k stores mapped", "tools": [ "BigQuery", "PostgreSQL / PostGIS", "Scraping", "Labeling tools" ] }, { "name": "Models", "proof": "96.7% SKU accuracy", "tools": [ "YOLO · RT-DETR", "EfficientNet", "XGBoost", "LightGBM" ] }, { "name": "Serving", "proof": "24× faster, −82% cost", "tools": [ "Rust · Axum", "ONNX Runtime", "CUDA", "Kubernetes" ] }, { "name": "Agents", "proof": "812k+ messages", "tools": [ "MCP servers", "LLMs on Vertex AI", "Slack · WhatsApp", "Eval sets" ] }, { "name": "Product", "proof": "2 products founded", "tools": [ "TypeScript · React", "Go · Python APIs", "GCP · AWS", "Solidity" ] } ], "projects": [ { "id": "production-vision", "name": "Production computer vision platform (retail shelf recognition)", "role": "ML & AI Agentic Systems Lead (current role)", "section": "#ml-production", "oneLiner": "Turns shelf and store photos into brand, SKU and execution data; rebuilt end to end for speed and cost.", "details": [ "Owns 7 production models, 8 category pipelines and ~20 API endpoints.", "Rewrote a legacy Python/TensorFlow inference service as a 47 MB Rust binary on ONNX Runtime and moved it to autoscaled GPUs on Kubernetes.", "Fixed-shape batch padding removed ~5 s of cuDNN re-planning per photo (2.5 ms per product crop, identical outputs).", "Verified Keras → ONNX parity and face-blur parity (IoU ≥ 0.9); every crop is face-blurred before storage.", "Shipped in 10.5 weeks." ], "results": [ "Analyze a full shelf photo: 17 s → 0.7 s (24× faster)", "Recognize one product: 1.0 s → 0.17 s (6× faster)", "Monthly serving cost: $66.70 → $13.71 (−82%)", "Memory needed: 4.1 GiB → 1.2 GiB (−71%)", "8,833 production runs in 7 days with 0 errors; peak 3,287 runs/day.", "Recognize a product: 65 ms typical, 74 ms p95 (307 runs)", "Blur faces: 147 ms typical, 214 ms p95 (4,317 runs)", "Find all products: 167 ms typical, 201 ms p95 (702 runs)", "Privacy check: 302 ms typical, 470 ms p95 (1,411 runs)" ], "stack": [ "Rust", "Axum", "ONNX Runtime", "CUDA", "Kubernetes", "GPU autoscaling", "Pub/Sub", "BigQuery" ] }, { "id": "vision-models", "name": "Six computer-vision models", "role": "ML & AI Agentic Systems Lead (trained and evaluated end to end)", "section": "#model-lab", "oneLiner": "Product recognition, store-type, cooler, store-scene, shelf and storefront models — measured results below.", "details": [ "Product recognition: Identifies the brand, sub-brand and exact SKU of every product on a shelf.", "Store-type classification: Tells which of 11 store types each visit belongs to, from its photos.", "Cooler recognition: Recognizes the cold equipment in a store and which brand owns it.", "Store-scene detection: Finds signage, fridges, shelving, entrances and address plates in store photos.", "Shelf product detection: Locates every product on a crowded shelf so each one can be recognized.", "Storefront detection: Spots shops in street-level video to map new points of sale." ], "results": [ "Product recognition — 96.7% SKU accuracy; brands recognized 315, brand accuracy 97.1%, photos validated 31,311, recall after retrain 75% → 98.6%. Added 7 new SKUs at 97% accuracy with no new labeling round — ~$800 saved per extension.", "Store-type classification — 74% visits auto-resolved; store types 11, accuracy (auto) 93.4%, top-3 accuracy 97.2%, high-confidence 96.0%. Three of every four visits are classified with no human review; only doubtful ones reach a person.", "Cooler recognition — 95.1% equipment accuracy; brand accuracy 92.1%, brands 10, equipment types 3, response time 25 ms. Brand-level cooler audits answered in 25 ms per photo, live in production.", "Store-scene detection — −99.7% cost vs. LLM API; cost / 50k photos $200 → $0.59, time / photo 2–8 s → 50 ms, signage precision 85% mAP50, elements found 10 types. Replaced a paid LLM step: up to 160× faster, at about one cent per thousand photos.", "Shelf product detection — ~41 products per photo; response time 165 ms, full shelf analysis 17 s → 0.7 s, detections / week 3,524, production errors 0. Turns one shelf photo into ~41 recognized products in under a second.", "Storefront detection — $0 GPU cost to run; runs on any CPU, frames pre-labeled, annotator task accept / fix, output storefront boxes. Annotators start from the model's boxes instead of empty frames." ], "stack": [ "YOLO OBB", "RT-DETR", "EfficientNet", "ONNX", "Vertex AI" ], "caveats": [ "SKU accuracy was measured on 31,311 held-out photos split per photo (not per visit).", "The storefront detector has no published accuracy metric; it is used for CPU pre-labeling." ] }, { "id": "ai-agents", "name": "AI agents in operations", "role": "ML & AI Agentic Systems Lead (designer and operator)", "section": "#agent-platform", "oneLiner": "Two agent systems: a research agent that answers business questions from live data (Slack/WhatsApp, custom MCP server), and field agents on WhatsApp that guide store visits, validate photos and extract attributes.", "details": [ "Research agent: plain-language questions → domain skills/playbooks → custom MCP server (11 tools, OpenAPI auto-discovery) over the data warehouse, geo database and REST API → answers, maps, PDF reports, scheduled digests.", "Guardrails: read-only, SELECT-only, tenant-scoped queries; loop and prompt-injection rules; a 70-question evaluation set.", "Field agents: photo validation (~0.3 s), attribute extraction from images, voice note → questionnaire, duplicate detection, automatic face blur, store-name/address normalization and matching." ], "results": [ "812k+ messages handled (5.8k research questions + 806k field-capture messages.)", "321k+ AI & tool calls (LLM calls, data queries, photo checks, transcriptions.)", "355k field photos processed (Captured through the agents and checked by AI on arrival.)", "100+ people using them (Field teams on WhatsApp, ops and sales on Slack.)", "50,913 visits guided", "37,502 visits completed", "780k+ agent replies", "136,745 LLM calls", "1.7 s p50 LLM response", "70 eval questions", "Research-agent adoption: 487 questions in July → 2,500 in September (5×)." ], "stack": [ "LLM agents on Vertex AI", "MCP", "Python", "WhatsApp Cloud API", "speech-to-text", "BigQuery", "PostgreSQL/PostGIS", "Pub/Sub", "Slack" ] }, { "id": "reals-lab-valuation", "name": "Reals Lab — automated property valuation", "role": "Founder", "section": "#real-estate-avm", "oneLiner": "Every scraped listing gets a model-estimated fair value, so buyers instantly see under- and over-priced properties.", "details": [ "XGBoost models on price per m² for apartments and houses, using area, location, cadastral value, stratum, age, rooms and more.", "Each listing card shows the estimate and whether the asking price is below, near or above it." ], "results": [ "R² 0.88 on apartments, 0.80 on houses (hold-out)", "14.7% average error on apartments", "~18.5k listings monitored, scrapers run daily", "Live demo on this page: the production model runs in the browser (and via the estimate_property_value WebMCP tool)." ], "stack": [ "XGBoost", "ONNX", "Rust API", "TypeScript" ], "links": [ "https://realslab.xyz" ] }, { "id": "reals-lab-audit", "name": "Reals Lab — listing audit (anomaly detection)", "role": "Founder", "section": "#listing-audit", "oneLiner": "Checks each listing before buyers see it; inconsistent or suspicious listings are blocked.", "details": [ "Checks location vs GPS, area plausibility, price vs cadastral value and listing health; an ML model scores anomaly probability.", "Real example: a 96 m² apartment asking 24× its cadastral value per m² scored 99.98% anomaly probability and was rejected." ], "results": [ "8,268 listings audited across 6 segments", "~2,800 bad listings blocked", "93.4% average ROC-AUC, 97.8% best segment" ], "stack": [ "XGBoost", "LLM-assisted labeling", "Python" ], "links": [ "https://realslab.xyz" ] }, { "id": "risks-vision", "name": "Risks Vision — machine-learning crypto strategies, run by AI agents", "role": "Founder", "section": "#quant-trading-ml", "oneLiner": "Machine-learning trading strategies run by an AI-agent desk (scout reads markets, risk sets limits, runner runs the book). 102 strategies stress-tested on crypto and US-index data with real fees; the 8 survivors run as one portfolio.", "details": [ "No-lookahead research pipeline: data → features → signals → next-bar fills → reports; train ≤2023, validation 2024, test 2025+.", "A LightGBM filter turns a losing US100 opening-range rule (−0.09R) into a winning one (+0.26R) on test.", "A daily trade / no-trade signal and a weekly health check per strategy." ], "results": [ "Backtest 2020–2026: $100k → $702k vs $261k for the S&P 500", "33% CAGR vs 15% for the S&P 500; beta 0.02", "Profit factor 1.49 over 2,037 trades; max drawdown −13.4%", "Out-of-sample (2025+): profit factor 1.32 over 612 trades" ], "stack": [ "Python", "LightGBM", "pandas", "Binance / index data", "Telegram" ], "links": [ "https://risksvision.xyz" ], "caveats": [ "All returns are simulated backtests with fees included, not live trading returns." ] }, { "id": "retail-census", "name": "Geospatial retail census", "role": "Data systems (built the isochrones and census tooling)", "section": "#retail-census", "oneLiner": "A living map of traditional retail: every store, the potential of each zone, and where field teams should go next.", "details": [ "Isochrones: the logical division of each city — Bogotá 412, Cali 96, Medellín 93, Barranquilla 65.", "Simulated potential per isochrone, Pareto (fewest isochrones holding 80% of potential), coverage and daily route planning for field agents." ], "results": [ "~70k stores geolocated in 4 cities", "32.8k field-verified stores", "72k store visits", "666 isochrones", "Verified stores in 86% of Bogotá's isochrones" ], "stack": [ "PostGIS", "BigQuery", "Python", "geospatial analysis" ] }, { "id": "unreal-destiny", "name": "Unreal Destiny — blockchain RPG economy", "role": "Software engineer, smart contract developer, then DevOps tech lead (2021–2024)", "section": "#bbstudios", "oneLiner": "Every reward, trade and stake in a fantasy RPG settles on-chain through smart contracts.", "details": [ "DeFi-style game mechanics with transparent player ownership.", "Gameplay video: https://www.youtube.com/watch?v=UG8X_ICpddE" ], "results": [ "100k+ on-chain transactions", "Deployed on Polygon, Arbitrum and Meter" ], "stack": [ "Solidity", "Polygon", "Arbitrum", "Meter" ] } ], "faq": [ { "q": "What does Sebastian do?", "a": "Machine learning engineer with 7+ years building software, who takes models from data to production. He trains computer-vision models, serves them fast and cheap, and builds the AI agents and data platforms around them. Recently: rebuilt a retail vision inference service (24× faster, 82% cheaper), trained six vision models (up to 96.7% accuracy), and built AI agents that have handled 812k+ messages." }, { "q": "What is he best at?", "a": "Taking ML from data to production: computer-vision models, fast/cheap inference (Rust + ONNX + GPUs) and AI agents over live data." }, { "q": "Is he available?", "a": "Open to machine learning, computer vision and AI-agent roles, contracts and collaborations." }, { "q": "How do I contact him?", "a": "Email admin@risksvision.xyz with a short note about the system you want to build. Alternative: sebastianto1999@gmail.com. CV: /sebastian-torres-portfolio.pdf" }, { "q": "Where is he based?", "a": "Bogotá, Colombia" }, { "q": "What is his education?", "a": "Systems Engineering · Universidad Nacional de Colombia" }, { "q": "Which companies has he worked for?", "a": "Employer and client names are kept confidential on this portfolio. The work and metrics are real; ask Sebastian directly for references." }, { "q": "Something isn't covered here", "a": "If a detail (dates, education, salary, languages, references) is not in these tools, it is not published — say so and suggest emailing admin@risksvision.xyz. Do not guess." } ] }