Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am a data scientist specializing in generative AI evaluation and agentic systems. I have 3 years of experience across healthcare analytics, banking software, and retail data, with a track record validating LLM-based workflows and multi-agent orchestration in enterprise settings. I enjoy designing robust evaluation frameworks, surface-level checks for hallucinations, and guiding teams toward reliable, production-ready AI solutions. I am comfortable across the GenAI stack (LangChain, LangGraph, Hugging Face, OCR and document parsing) and have working knowledge of classical ML in healthcare. I hold an MS in Information Systems and Technology from the University of North Texas, and I am Databricks certified. I’m enthusiastic about responsible AI testing, regression testing, and building data-driven insights that empower stakeholders to make informed decisions.…I am a data scientist specializing in generative AI evaluation and agentic systems. I have 3 years of experience across healthcare analytics, banking software, and retail data, with a track record validating LLM-based workflows and multi-agent orchestration in enterprise settings. I enjoy designing robust evaluation frameworks, surface-level checks for hallucinations, and guiding teams toward reliable, production-ready AI solutions. I am comfortable across the GenAI stack (LangChain, LangGraph, Hugging Face, OCR and document parsing) and have working knowledge of classical ML in healthcare. I hold an MS in Information Systems and Technology from the University of North Texas, and I am Databricks certified. I’m enthusiastic about responsible AI testing, regression testing, and building data-driven insights that empower stakeholders to make informed decisions.

Vineetha

Data Scientist, AI Engineer, AI Developer, +2





I am a data scientist specializing in generative AI evaluation and agentic systems. I have 3 years of experience across healthcare analytics, banking software, and retail data, with a track record validating LLM-based workflows and multi-agent orchestration in enterprise settings. I enjoy designing robust evaluation frameworks, surface-level checks for hallucinations, and guiding teams toward reliable, production-ready AI solutions. I am comfortable across the GenAI stack (LangChain, LangGraph, Hugging Face, OCR and document parsing) and have working knowledge of classical ML in healthcare. I hold an MS in Information Systems and Technology from the University of North Texas, and I am Databricks certified. I’m enthusiastic about responsible AI testing, regression testing, and building data-driven insights that empower stakeholders to make informed decisions.…I am a data scientist specializing in generative AI evaluation and agentic systems. I have 3 years of experience across healthcare analytics, banking software, and retail data, with a track record validating LLM-based workflows and multi-agent orchestration in enterprise settings. I enjoy designing robust evaluation frameworks, surface-level checks for hallucinations, and guiding teams toward reliable, production-ready AI solutions. I am comfortable across the GenAI stack (LangChain, LangGraph, Hugging Face, OCR and document parsing) and have working knowledge of classical ML in healthcare. I hold an MS in Information Systems and Technology from the University of North Texas, and I am Databricks certified. I’m enthusiastic about responsible AI testing, regression testing, and building data-driven insights that empower stakeholders to make informed decisions.

Available to hire

I am a data scientist specializing in generative AI evaluation and agentic systems. I have 3 years of experience across healthcare analytics, banking software, and retail data, with a track record validating LLM-based workflows and multi-agent orchestration in enterprise settings. I enjoy designing robust evaluation frameworks, surface-level checks for hallucinations, and guiding teams toward reliable, production-ready AI solutions.

I am comfortable across the GenAI stack (LangChain, LangGraph, Hugging Face, OCR and document parsing) and have working knowledge of classical ML in healthcare. I hold an MS in Information Systems and Technology from the University of North Texas, and I am Databricks certified. I’m enthusiastic about responsible AI testing, regression testing, and building data-driven insights that empower stakeholders to make informed decisions.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

GenAI Software Automation Engineer at Wells Fargo

August 1, 2025 - December 1, 2025

Contributed to validation of multi-agent banking systems migrating from single-shot RAG pipelines to agentic LangGraph workflows; added test cases and Pytest utilities to the evaluation harness; implemented LLM-as-judge faithfulness and groundedness checks; surfaced hallucinations, broken tool calls, and incorrect handoffs pre-production. Helped validate MCP server integrations and tool-use planning, including function-calling schemas, structured outputs, retry semantics, and observability traces across agent runs. Reviewed RAG and agentic retrieval quality across PDF-to-text extraction, OCR, chunking strategies, embeddings, vector retrieval, semantic search, and hybrid search; tracked context precision, context recall, and citation coverage. Collaborated with QA, product, and engineering stakeholders on release readiness and regression testing for prompts and agent trajectories.

Data Scientist at Cigna Healthcare

June 1, 2024 - December 1, 2024

Prepared clinical, claims, and operational datasets using Python, SQL, Pandas, NumPy, and Scikit-learn to support analytics, modeling, and decision-support with HIPAA-aligned PHI handling. Trained and compared classification model variants (Logistic Regression, Random Forest, XGBoost, LightGBM) for utilization and risk insights; reported precision, recall, F1, ROC-AUC, and confusion matrices on holdout. Supported RAG-based healthcare knowledge workflows by validating document parsing, OCR outputs, chunking strategy, embeddings, vector retrieval, semantic search, and hybrid search for clinical references. Built and maintained Power BI dashboards with DAX measures and SQL views, tracking utilization, risk-scoring, and KPI metrics. Applied GenAI response-quality checks including relevance, groundedness, completeness, hallucination detection, and human review feedback.

Software Developer at HDFC Bank

February 1, 2023 - June 1, 2024

Built and maintained banking workflow features in Python and SQL; supported data processing, internal system integrations, and operational reporting. Wrote Pytest unit and integration tests, executed API validation, and supported defect triage to improve reliability and data accuracy. Optimized SQL queries, stored procedures, and reconciliation routines; supported reporting logic and DBMS activities. Participated in Azure-based cloud modernization, CI/CD pipelines, and release validation; collaborated with QA, BAs, and stakeholders to translate requirements into test evidence and ship sprint-level enhancements.

Data Analyst at Reliance

June 1, 2022 - January 1, 2023

Analyzed retail data across sales, inventory, customer behavior, product movement, and store performance using SQL, Excel, and Power BI; produced Tableau views where applicable. Built and maintained dashboards covering sales trends, category performance, regional performance, inventory movement, promotion impact, and operational KPIs. Wrote SQL queries against Oracle and MySQL, validated datasets with Excel, and generated weekly/monthly KPI reports for retail operations, merchandising, and business teams.