AI Engineer specializing in Generative AI, Retrieval-Augmented Generation (RAG), and cloud-native deployments. I develop domain-specific AI systems that drive measurable business impact across industries—from banking and finance to enterprise automation. With hands-on expertise in LangChain, LangGraph, MCP Server, and Azure Cloud, I design scalable, efficient solutions that improve accuracy, performance, and user experience. My work includes fine-tuning large language models (LoRA/QLoRA, PEFT) on proprietary datasets, building RAG-powered applications, fraud detection systems, analytics dashboards, and data governance frameworks. I focus on transforming complex challenges into streamlined, high-impact solutions.

Cristian Vega

AI Engineer specializing in Generative AI, Retrieval-Augmented Generation (RAG), and cloud-native deployments. I develop domain-specific AI systems that drive measurable business impact across industries—from banking and finance to enterprise automation. With hands-on expertise in LangChain, LangGraph, MCP Server, and Azure Cloud, I design scalable, efficient solutions that improve accuracy, performance, and user experience. My work includes fine-tuning large language models (LoRA/QLoRA, PEFT) on proprietary datasets, building RAG-powered applications, fraud detection systems, analytics dashboards, and data governance frameworks. I focus on transforming complex challenges into streamlined, high-impact solutions.

Available to hire

AI Engineer specializing in Generative AI, Retrieval-Augmented Generation (RAG), and cloud-native deployments. I develop domain-specific AI systems that drive measurable business impact across industries—from banking and finance to enterprise automation. With hands-on expertise in LangChain, LangGraph, MCP Server, and Azure Cloud, I design scalable, efficient solutions that improve accuracy, performance, and user experience.
My work includes fine-tuning large language models (LoRA/QLoRA, PEFT) on proprietary datasets, building RAG-powered applications, fraud detection systems, analytics dashboards, and data governance frameworks. I focus on transforming complex challenges into streamlined, high-impact solutions.

See more

Experience Level

Expert
Expert
Expert
Expert

Work Experience

Senior AI Engineer at Morf Health
September 1, 2022 - Present
Led development of a production-grade, voice-enabled AI assistant for healthcare professionals, delivering real-time clinical decision support, streamlined workflows, and personalized care recommendations in active hospital environments. Built a conversational AI platform with Retrieval-Augmented Generation (FAISS, Weaviate), enabling accurate, context-aware responses from medical guidelines, EHRs, and treatment protocols — reducing manual lookups for clinicians. Architected a multi-agent AI system with role-based agents — Clinical Advisor, Risk Assessor, and Care Planner — designed to collaborate autonomously through natural voice dialogue to support medical staff. Fine-tuned GPT and LoRA/QLora on proprietary clinical data, improving medical relevance, safety, and conversational depth for real-world patient care scenarios. Established LLM Ops infrastructure using MLflow, Weights & Biases, and human-in-the-loop review processes to ensure reliability, traceability, and HIPAA-compl
Data Scientist at GumGum
January 1, 2021 - August 1, 2022
Developed NLP and semantic enrichment models to extract sentiment, intent, and product attributes from large-scale reviews and content data, enhancing GumGum's contextual intelligence pipeline for CTV and digital ad targeting. Built feature extraction pipelines for tokenization, embeddings, and entity linking to generate structured, context-aware metadata used for content classification, brand suitability, and ad performance signals. Applied topic modeling, clustering, and sentiment analysis to align consumer language with CTV audience segments, content categories, and performance signals. Conducted offline evaluation and A/B tests to measure the impact of semantic enrichment on engagement metrics. Designed analytics dashboards to monitor semantic tagging coverage, sentiment trends, CTV performance metrics. Collaborated with product, ad operations, and UX teams to translate semantic data into actionable ad placement decisions and reporting.
Machine Learning Researcher at ClearBlade
May 1, 2019 - November 1, 2020
Led applied research in anomaly detection and unsupervised learning to uncover financial fraud, cyber intrusions, and operational risks across large-scale enterprise systems. Developed and benchmarked ML algorithms — including clustering, autoencoders, Bayesian inference, and graph-based methods — to reveal rare and complex patterns in high-dimensional data. Built Python ML prototypes using scikit-learn, TensorFlow, and Theano, then optimized and refactored them into production-grade pipelines for real-time analytics. Partnered with data engineering to aggregate, clean, and standardize vast transaction data sets, ensuring model reliability and reproducibility. Authored and presented research papers, patents, and internal white papers, advancing the company’s IP portfolio. Collaborated with product management and security engineers to embed research outputs into customer-facing fraud detection and threat monitoring tools for global financial clients. Investigated early deep learni
Python Data Engineer at Dell Technologies
June 1, 2017 - May 1, 2019
Engineered Python-based data pipelines to ingest, transform, and manage large-scale operational and product telemetry data for Dell’s Data & Analytics Platform, enabling data-driven insights across client and cloud offerings. Optimized data ingestion and storage workflows using PostgreSQL, Hadoop, and AWS S3, improving throughput and reliability for analytics dashboards and AI-driven decision systems across Dell hardware and cloud offerings. Col laborated with analytics and product engineering teams to pre-process, normalize, and enrich device performance and customer usage data—supporting predictive analytics, warranty intelligence, and proactive support features. Automated data quality validation, anomaly detection, and schema consistency checks using NumPy, Pandas, and scikit-learn, reducing data pipeline failures and inconsistent records by 30%. Developed internal REST APIs and data services to provide secure, scalable access to product telemetry and analytics datasets for engi

Education

Bachelor of Computer Science at University of Texas at Austin
August 1, 2013 - May 1, 2017

Qualifications

Add your qualifications or awards here.

Industry Experience

Media & Entertainment, Healthcare, Software & Internet, Professional Services