THIAGO ANTAS

Senior AI Solutions Architect | Agentic AI & LLM Expert | Enterprise Systems Leader

Cascais / Lisbon, Portugal · thiago@thiago.pt · +351 912 699 268 linkedin.com/in/tfantas · github.com/tfantas · thiagoantas.com · ORCID 0009-0000-9408-5663

Professional Summary

Results-driven Senior AI Solutions Architect with 21+ years of experience designing enterprise-scale systems. Deep expertise in Agentic AI, LLM Orchestration (GPT-4, Claude, Llama, Mistral, DeepSeek), RAG Systems, and MLOps/LLMOps. Track record of architecting autonomous AI agents and cloud-native systems processing 2M+ events/day with 99.9% uptime. Led digital transformation for Fortune 500 clients achieving $2M+ annual savings. Co-founded a startup scaled to 50,000+ users. Now also delivering native, on-device AI applications across Apple platforms (iOS 26 / macOS). Expert in AWS Bedrock, GCP Vertex AI, and LangChain/LangGraph.

Core Competencies

• Agentic AI & Autonomous Systems: AI Agents Architecture, Multi-Agent Systems (CrewAI, AutoGen, LangGraph), Agent Orchestration, Tool Calling, Function Calling, MCP Protocol
• LLM Engineering & MLOps: LLM Fine-tuning (LoRA, QLoRA, RLHF), RAG Pipelines, Prompt Engineering, LLMOps, Vector DBs (Pinecone, Weaviate, Qdrant), LangSmith, Weights & Biases
• Cloud AI Platforms: AWS Bedrock, GCP Vertex AI, Azure OpenAI, AWS (EKS, Lambda, SageMaker), Kubernetes, Terraform, Cloudflare Workers
• Apple Platform & Native Development: Swift 6.2, SwiftUI, Liquid Glass, AppKit, On-Device LLM/STT, Real-Time Transcription & Translation (iOS 26 / macOS)
• Architecture & Development: Event-Driven Architecture, Microservices, CQRS, DDD, API Design (REST, GraphQL, gRPC)
• Languages & Frameworks: Python, Rust, TypeScript, Java, Go | LangChain, FastAPI, Spring Boot, Node.js, React

Professional Experience

Capgemini — Lisbon, Portugal

Senior AI & Software Architect / Tech Lead | 2018 – Present (7+ years)

• Architected enterprise AI agent systems using LangGraph and CrewAI, achieving 40% reduction in customer support response times
• Designed production RAG pipelines processing 2M+ daily queries with LangChain, Pinecone, and AWS Bedrock with 99.9% uptime SLA
• Implemented LLMOps infrastructure with LangSmith and Weights & Biases, reducing model deployment cycles from weeks to hours
• Led cloud migration of 200+ applications to AWS/Kubernetes, achieving 45% infrastructure cost reduction (~$1.2M/year)
• Architected event-driven systems processing 500K+ transactions/hour using Spring Boot, Kafka, and PostgreSQL
• Built multi-agent orchestration systems integrating GPT-4, Claude, and Llama via the MCP Protocol
• Delivered native, on-device AI applications for Apple platforms (iOS 26 / macOS) in Swift 6.2 & SwiftUI, integrating real-time speech-to-text, LLM reasoning, and live translation
• Engaged across regulated public-sector and insurance programs (incl. Portuguese Social Security), pairing RAG, Databricks, and Mistral AI with security-first enterprise governance
• Mentored 15+ engineers in cloud architecture, DevOps, and emerging AI integration patterns
• Received FCT (Portuguese Foundation for Science and Technology) recognition for technical excellence

Urban Mobility Startup — Rio de Janeiro, Brazil

Co-Founder & CTO | 2016 (1 year)

• Scaled platform from MVP to 50,000+ active users within 18 months, securing R$100K seed funding
• Built real-time geolocation system with ML-powered route optimization, reducing delivery times by 30%
• Led technical team of 8 engineers; designed full-stack architecture (React Native, Node.js, PostgreSQL, Redis)

Earlier Career | 2004 – 2017 (13 years)

• Progressive technical leadership at Above-Net, Druid, Noorden Group, Petrobras, SulAmérica Seguros, Gazeus Games, ProBid, Politec, and TOTVS
• Architected high-availability trading systems, led SOA and microservices implementations, and managed offshore development teams across Energy, Insurance, Gaming, and Financial Services

Key Projects & Achievements

• Second Brain — iOS 26 Native App: Real-time cognitive-augmentation app for Apple platforms — Swift 6.2, SwiftUI, Liquid Glass — featuring on-device speech-to-text, LLM reasoning, and live translation through a multi-agent architecture
• Brain Core Engine: High-performance retrieval core powering Second Brain — Voyage 3.5 embeddings with a Qdrant vector database and HNSW indexing, delivering sub-200ms semantic search
• macOS Native Development Blueprint: Hardware-aware, AI/LLM-optimized blueprint for native macOS development, tuned for Intel MacBook Pro 16,4 (Late 2019 — Core i9, Radeon Pro 5600M)
• Enterprise RAG Platform: Production-grade retrieval system using LangChain, Pinecone, and OpenAI embeddings for a 100K+ document corpus with semantic search
• AI Agent Orchestration Framework: Custom LangGraph framework for autonomous multi-step task execution with human-in-the-loop governance
• Zero-Downtime K8s Migration: Migrated 1000+ microservices to Kubernetes clusters, achieving 60% cost reduction
• 1,300+ Private GitHub Repositories: Continuous innovation portfolio across AI/ML, Agentic AI, DevOps, and enterprise architecture

Education & Certifications

• Professional Certificate in AI and Machine Learning — Purdue University | Jul 2025 – Feb 2026 Purdue PCP AIML Cohort 82 — Applied Data Science, ML, Deep Learning, GenAI, RAG, Prompt Engineering
• MBA in Software Engineering — UFRJ, Federal University of Rio de Janeiro | 2013 – 2014
• Bachelor’s in Information Systems | 2007 – 2011 · Technical Degree in Computer Science | 2003 – 2005
• Core Expertise Areas: AWS Solutions Architecture | Kubernetes Administration | Agile (Scrum Master, Scrum Developer) | DevOps & CI/CD
• AI/ML (Purdue 2025–2026): Deep Learning | ML with Python | TensorFlow | GANs | Supervised/Unsupervised ML | Prompt Engineering | RAG | Databricks | ChatGPT Advanced

Technical Stack

• AI/LLM: GPT-4, Claude, Llama, Mistral, DeepSeek | LangChain, LangGraph, CrewAI, AutoGen | RAG, Vector DBs (Pinecone, Weaviate, ChromaDB, Qdrant) | Voyage embeddings, HNSW | LoRA/QLoRA Fine-tuning | LangSmith, W&B
• Cloud: AWS (Bedrock, SageMaker, EKS, Lambda) | GCP Vertex AI | Azure OpenAI | Cloudflare Workers | Vercel, Supabase
• Infrastructure: Kubernetes, Docker, Terraform, Helm, ArgoCD | GitHub Actions, GitLab CI/CD | Kafka, RabbitMQ, Redis
• Apple Platforms: Swift 6.2, SwiftUI, Liquid Glass, AppKit | On-Device LLM/STT, Real-Time Transcription & Translation (iOS 26 / macOS)
• Languages: Python, Rust, TypeScript, Java, Go, SQL | FastAPI, Spring Boot, Node.js, React, Next.js

Languages

Portuguese (Native) · English (Fluent) · Spanish (Basic)

Online Profiles & Competitive Programming

• GitHub — github.com/tfantas 1,300+ private repositories (AI/ML, Agentic AI, DevOps, enterprise architecture) · GitHub Developer Program Member · Achievements: Pull Shark ×3, Pair Extraordinaire, Quickdraw, YOLO
• HackerRank — hackerrank.com/profile/tfantas 14 verified certifications — Problem Solving (Basic, Intermediate); SQL (Basic, Intermediate, Advanced); Python (Basic); Java (Basic); JavaScript (Basic, Intermediate); React (Basic); Node (Basic); REST API (Intermediate); CSS (Basic); Software Engineer (Role). Earned badges in Problem Solving, Java, Python & Days of Code.
• Professional Certifications (2025): Purdue PCP AIML (Cohort 82) · 16× Simplilearn SkillUp — Generative AI, Deep Learning, ML with Python/R, TensorFlow, GANs, Prompt Engineering, RAG, DeepSeek, Mistral AI, ChatGPT Advanced, Data Analytics · 3× Databricks — SQL Analytics & BI, Generative AI, for Business Leaders
• ORCID — 0009-0000-9408-5663

Last updated: 18 June 2026