Bobby Santiago - AI Engineer Resume

const puppeteer = require('puppeteer'); const fs = require('fs'); const path = require('path'); const resumeHTML = ` Bobby Santiago - AI Engineer Resume

Professional Summary

AI Engineer with more than a decade of full-stack development experience, specializing in integrating Large Language Models (LLMs) and machine learning systems into production applications. Currently building intelligent systems using FastAPI, open-source models, and RAG architectures while leveraging deep expertise in Ruby on Rails for scalable backend development. Proven track record implementing NLP solutions, fine-tuning models for domain-specific tasks, and optimizing AI workloads for enterprise-scale deployments.

Core Competencies

AI & Machine Learning

LLM Integration (GPT-4, Claude)
RAG Systems & Semantic Search
Fine-tuning & Optimization
FastAPI & ML Pipelines
Vector Databases
Prompt Engineering

Backend Development

Ruby on Rails
Python (FastAPI, Flask)
RESTful & GraphQL APIs
PostgreSQL, Redis, MongoDB
Microservices Architecture
Real-time Data Processing

AI Infrastructure

Model Deployment & Serving
GPU Optimization
Streaming & WebSockets
Background Job Processing
Performance Monitoring
Cost Optimization

Professional Experience

AI Engineer & Technical Consultant

Independent | June 2022 - Present

Architected and deployed production RAG system processing 100K+ documents using LangChain, achieving 95% accuracy in semantic search
Built intelligent content classification system using fine-tuned Llama 2 models, reducing manual review time by 80%
Developed FastAPI microservices for real-time AI inference, handling 1000+ requests/second with sub-200ms latency
Implemented streaming chat interfaces with GPT-4 and Claude APIs for customer support automation
Created custom embedding pipelines using Sentence Transformers for domain-specific similarity matching
Integrated vector databases (Pinecone) with Rails applications for scalable semantic search capabilities

Senior Software Engineer (AI/ML Focus)

SurveyMonkey | June 2016 - June 2022

Built NLP-powered response analysis system processing 10M+ survey responses monthly using BERT-based models for sentiment analysis and topic classification
Implemented ML pipeline for automatic survey response tagging, achieving 92% accuracy and reducing manual categorization by 75%
Developed real-time anomaly detection system using statistical models to identify response patterns and data quality issues
Created predictive analytics features using time-series forecasting to help customers anticipate CX trends
Optimized data processing pipeline handling millions of responses with sub-second query performance
Led technical architecture for SurveyMonkey CX platform launch, delivered within 6-month deadline

Senior Software Engineer

chideo.com | August 2014 - June 2016

Led Ruby on Rails application redesign for improved performance and scalability under high-traffic loads
Designed RESTful API endpoints enabling seamless third-party integrations
Implemented containerization and CI/CD pipelines, reducing deployment cycles

Software Developer

Seso Media LLC / A Hundred Years | February 2013 - August 2014

Engineered full-stack web applications for clients including TED Ed and The Smithsonian
Developed backend APIs and frontend interfaces for data-driven web experiences

Recent AI Projects

Intelligent Document Processing: Built RAG system using LangChain and GPT-4 for automated contract analysis
Custom AI Agent Framework: Developed multi-agent system for complex task automation using Claude API
Fine-tuned Classification Models: Achieved 94% accuracy on domain-specific text classification using Llama 2
Real-time AI Chat System: Implemented WebSocket-based streaming chat with context management
Semantic Search Engine: Created vector search system processing 500K+ documents with sub-100ms response time

Technical Skills

AI/ML Technologies: LangChain, Hugging Face Transformers, OpenAI API, Anthropic Claude, Llama 2/3, BERT, GPT-4, Sentence Transformers, scikit-learn, PyTorch

Vector Databases: Pinecone, Weaviate, Chroma, pgvector

Languages: Python, Ruby, JavaScript, SQL

Frameworks: FastAPI, Flask, Ruby on Rails, React, Next.js

Infrastructure: Docker, Kubernetes, AWS SageMaker, Model serving (TorchServe, Triton)

Data Processing: Pandas, NumPy, Apache Spark, Redis, Celery, Sidekiq

Key Achievements

Reduced costs 60% by implementing efficient prompt engineering and caching strategies for LLM applications
Improved accuracy from 72% to 95% in document classification through fine-tuning and RAG implementation
Scaled AI system to 10M+ requests/month with 99.9% uptime using microservices architecture
Decreased response time by 85% through GPU optimization and model quantization techniques
Built production NLP pipeline processing millions of survey responses with real-time insights

Education

Bachelor of Science in Electrical Engineering
University of Massachusetts, Amherst | 1987 - 1991
Field of Specialization: Telecommunications | Honors: Dean's List

`; async function generatePDF() { const browser = await puppeteer.launch(); const page = await browser.newPage(); await page.setContent(resumeHTML, { waitUntil: 'networkidle0' }); const pdfPath = path.join(__dirname, 'public', 'bobby-santiago-resume.pdf'); // Ensure public directory exists if (!fs.existsSync(path.join(__dirname, 'public'))) { fs.mkdirSync(path.join(__dirname, 'public')); } await page.pdf({ path: pdfPath, format: 'Letter', printBackground: true, margin: { top: '0.5in', right: '0.5in', bottom: '0.5in', left: '0.5in' } }); await browser.close(); console.log(`PDF generated successfully at: ${pdfPath}`); } generatePDF().catch(console.error);

Articles

Background

Page Not Found