Enterprise RAG Assistant
Developed enterprise-grade retrieval assistants using GPT-4, LangChain, Vertex AI, embeddings, and document pipelines to support high-accuracy Q&A and knowledge search across business documents.
Data Scientist with AI/ML, NLP, cloud data engineering, and production deployment experience.
I build machine learning pipelines, GenAI applications, RAG assistants, forecasting models, and analytics workflows across Python, SQL, PySpark, Databricks, Snowflake, Azure, AWS, and GCP. My focus is practical: clean data, measurable models, reliable deployment, and insights leaders can act on.
My background combines data engineering depth with applied machine learning and GenAI delivery. I can move from raw data and messy requirements to analysis, modeling, APIs, dashboards, and production-ready workflows.
A recruiter-friendly skill map for Data Scientist, AI Scientist, ML Engineer, and Applied AI roles.
Selected examples rewritten from the resume as portfolio-style case studies for a Data Scientist position.
Developed enterprise-grade retrieval assistants using GPT-4, LangChain, Vertex AI, embeddings, and document pipelines to support high-accuracy Q&A and knowledge search across business documents.
Integrated Generative AI and reusable ML models to support demand forecasting, operational risk mitigation, and supply chain insight generation through automated data workflows.
Integrated ChatGPT APIs into client-facing workflows, reducing manual support work through contextual interactions and dynamic, production-ready chatbot responses.
Built Spark Structured Streaming and Kafka pipelines with validation checks, anomaly handling, data profiling, and warehouse-ready models for high-volume analytics.
Positioned for Data Scientist roles while keeping the strongest ML, analytics, and cloud delivery details visible.
Build end-to-end ML and GenAI pipelines for forecasting, document intelligence, RAG assistants, and production APIs. Use Python, FastAPI, GPT-4, LangChain, Vertex AI, Snowflake, Azure Data Factory, Databricks, PySpark, Kafka, Docker, Kubernetes, and CI/CD to deliver scalable data science workflows.
Delivered NLP, LLM, recommendation, migration, and analytics solutions using Python, Spark, Azure OpenAI, LangChain, Vertex AI Pipelines, Kubeflow, Airflow, Kafka, Snowflake, Redshift, Tableau, and Power BI. Improved prompt quality, reduced hallucinations, automated manual work, and operationalized data quality checks.
Created modern cloud data solutions for analytics and visualization. Built Python, SQL, PySpark, Azure Data Factory, Databricks, Synapse, Data Lake, TensorFlow, and Tableau-connected workflows for data cleansing, transformation, migration, EDA, and client usage trend analysis.
Academic foundation with healthcare, science, technology, and user-centered design context.
Useful for communicating analytics, designing dashboards, and making AI systems more usable for business stakeholders.
Business and operations foundation for translating model outputs into measurable decisions.
Scientific foundation in data quality, analysis, validation, and evidence-based decision-making.
Additional credentials that support technical leadership, cloud awareness, and secure AI delivery.
Delivery, stakeholder alignment, scope, and execution discipline.
Security-minded development for data, ML, and cloud environments.
Cloud foundation for data platforms and AI services.
Workflow, service operations, and enterprise platform knowledge.
Open to Data Scientist, Applied AI, ML Engineer, GenAI Engineer, and Data Science Analytics roles.
Data Scientist with hands-on GenAI, NLP, RAG, MLOps, Python, PySpark, SQL, Databricks, Snowflake, Azure, AWS, and GCP experience. Comfortable working with stakeholders, translating model performance into business outcomes, and delivering analytics that are explainable and production-ready.