Thiago Silva

Senior

Engenheiro de IA

Quem sou eu?


Passion for Technology

Driven by a genuine passion for technology, I have built my career in dynamic and innovation-driven environments.

I enjoy exploring emerging technologies, solving complex problems, and transforming ideas into solutions that create real-world impact.

Enterprise AI Engineer

My journey evolved from Data Engineering and distributed systems to designing and delivering enterprise AI solutions.

By combining strong engineering foundations with Generative AI, I build scalable, secure, and production-ready systems that solve complex business challenges.

Colaboração Global

I thrive in multicultural environments and enjoy collaborating with teams and clients across the globe.

I believe the best solutions emerge when technical excellence, diverse perspectives, and strong communication come together toward a common goal.

What I've Delivered

Production-ready systems that improved efficiency, enabled better decisions, and created value for global organizations.

a person holding a smart phone and a credit card
Mastercard – Enterprise AI Assistant SDK

Designed and developed an enterprise AI Assistant SDK for Mastercard, enabling banks to integrate secure AI capabilities into their platforms. Implemented guardrails, PII protection, and responsible AI controls to ensure compliance, security, and production readiness for sensitive financial data.

a close up of a cell phone with icons on it
Microsoft – Copilot Studio Evaluation & AI Agents

Built and evaluated AI agents using Copilot Studio and real-world business scenarios. Developed analytics and performance frameworks that generated actionable feedback for Microsoft teams, helping improve agent orchestration, user experience, and platform capabilities.

Alberta Health – Healthcare AI Assistant

Led the development of a healthcare AI assistant capable of answering medical questions, providing location-based healthcare recommendations, promoting public health campaigns, and guiding users during emergency situations. Built with a strong focus on reliability, responsible AI, and user experience for a large-scale public healthcare environment.

See more projects

Competências Principais

IA Generativa e LLMs

Construção de assistentes de IA e chatbots escaláveis e seguros.

Projeto fluxos de trabalho inteligentes e multiagentes que podem resolver de forma autônoma tarefas corporativas complexas, priorizar a segurança do usuário e fornecer informações altamente precisas.

NLP, Embeddings e Busca Vetorial

Transformando quantidades massivas de texto não estruturado em conhecimento pesquisável e acionável.

Utilizo bancos de dados vetoriais e técnicas avançadas de embedding para impulsionar buscas semânticas ultrarrápidas e sensíveis ao contexto, permitindo que os sistemas de IA compreendam profundamente a linguagem humana e forneçam respostas contextuais altamente precisas.


Geração Multimodal

Arquitetando pipelines para a criação de áudio, imagens e vídeos sintéticos. Construo orquestradores inteligentes capazes de combinar perfeitamente diferentes soluções generativas em experiências multimídia coesas e altamente envolventes.

Engenharia e Arquitetura

Projetando arquiteturas e microsserviços robustos e de alto desempenho capazes de suportar simultaneidade massiva de usuários. Construo as APIs essenciais e os pipelines de dados automatizados que conectam perfeitamente a lógica de negócios complexa a modelos avançados de IA.

Infraestrutura em Nuvem e DevOps

Implantando modelos de IA confiáveis e prontos para produção em ambientes escaláveis baseados em nuvem.

Implemento pipelines automatizados de integração e entrega contínuas (CI/CD) para otimizar as atualizações, garantindo estabilidade de nível corporativo e desempenho otimizado.

Entrega Ágil e Excelência em Engenharia

Impulsionando a execução fluida de projetos complexos de IA por meio de metodologias Ágeis e gerenciamento estruturado de tarefas via Jira.

Priorizo práticas de código limpo e documentação técnica abrangente, ao mesmo tempo em que promovo uma comunicação aberta e transparente entre equipes multifuncionais para garantir alinhamento, colaboração contínua e a entrega bem-sucedida do produto.

Tech Stack

A full breakdown of technologies, services, and libraries that I have experience with

Generative AI

Focusing on state-of-the-art implementation and orchestration.

Frameworks: LangChain, LlamaIndex, LangGraph, Langflow, CrewAI.

Model Providers: OpenAI (Since GPT-3), Anthropic, Google (Gemini), Mistral, Meta (Since Llama 2), AWS Bedrock.

Generative Media: ComfyUI (Custom Node Workflows), Stable Diffusion (XL/Flux.1), Midjourney, Google Veo, Runway Gen-3.

Techniques: RAG (Retrieval-Augmented Generation), Fine-tuning (LoRA), Prompt Engineering, Vision-Language Models (VLM).

Foundations: Embeddings (OpenAI, HuggingFace)

Responsible AI

Engineering defensive AI architectures, ensuring ethical governance through red teaming and automated guardrails.

Threat Mitigation: Prompt Injection (Direct & Indirect), Payload Splitting, Jailbreaking defense.

Red Teaming: Adversarial Testing, LLM Vulnerability Scanning, OWASP Top 10 for LLMs.

Guardrails: AWS Bedrock Guardrails, LangChain Guardrails, Data Anonymization, Content Filtering.

AI Observability & Evaluation

To monitor model performance, hallucination rates, and system latency.

Evaluation: LLM-as-a-Judge (G-Eval), DAG, QAG.

Benchmarking: Agentic Trajectory Accuracy, Hallucination Detection.

Tracing & Logging: Langfuse, LangSmith.

LMOps: Cost/Latency Analytics, Semantic Caching.

Data Engineering & ETL

Building high-throughput data pipelines and automated ETL processes

Orchestration: AWS Glue, Airflow, Argo Workflows.

Extraction: Scrapy, Selenium, Beautiful Soup.

Data Modeling, ETL Pipelines, Large Scale Datasets.

Databases & Vector Search

Designing hybrid storage strategies that combine traditional relational data with optimized vector search.

Storage: PostgreSQL, MongoDB, MySQL, Microsoft SQL Server.

Vector & Graph: ChromaDB, Neo4j, Amazon OpenSearch.

Cloud Storage: AWS S3, Azure Blob Storage, Google Cloud.

Computer Vision & ML

Extracting actionable insights from visual data through traditional image manipulation, custom OCR pipelines, and modern object detection architectures.


Vision: OpenCV, Detectron2, Tesseract OCR, GPT-Vision.

Frameworks: PyTorch, TensorFlow, Keras, Scikit-learn.

Processing: Video file manipulation, Pillow, NumPy, Word2Vec.

Cloud & Infrastructure

Managing scalable workloads

AWS Ecosystem: Amazon EC2, Bedrock, Lambda, S3.

Compute: Kubernetes, Docker, Linux.

Architecture: Microservices, Data Lakes.

MLOps & Deployment

Designing hybrid storage strategies that combine traditional relational data with optimized vector search.

Serving: FastAPI, Flask, Streamlit.

CI/CD: GitHub Actions , Argo Workflows , Canary, Version Control.

Messaging: RabbitMQ , Celery.

Software & Automation

Applying expert-level software engineering standards

Languages: Python, SQL, Batch Processing.

Tooling: SQLAlchemy, AsyncIO, Requests, PyQt5.

Quality: Pytest , Documentation, Poetry/Conda.

Contact


LinkedInWhatsAppEmail