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

AI/ML Engineer with 4+ years of experience in GenAI, machine learning, fraud detection, and financial analytics. I’ve built RAG pipelines, risk-scoring models, ML APIs, and reliable cloud data workflows while partnering closely with product, finance, data science, and engineering teams. Known for owning technical delivery end-to-end—improving LLM answer relevance and reducing hallucinations, scaling vector search over large document sets, deploying guarded LLM services with monitoring, and accelerating finance reporting and reconciliation through robust ETL and data validation.…AI/ML Engineer with 4+ years of experience in GenAI, machine learning, fraud detection, and financial analytics. I’ve built RAG pipelines, risk-scoring models, ML APIs, and reliable cloud data workflows while partnering closely with product, finance, data science, and engineering teams. Known for owning technical delivery end-to-end—improving LLM answer relevance and reducing hallucinations, scaling vector search over large document sets, deploying guarded LLM services with monitoring, and accelerating finance reporting and reconciliation through robust ETL and data validation.

YESWANTH SAI TIRUMALASETTY

AI Engineer, Data Engineer, Programmer, +2





AI/ML Engineer with 4+ years of experience in GenAI, machine learning, fraud detection, and financial analytics. I’ve built RAG pipelines, risk-scoring models, ML APIs, and reliable cloud data workflows while partnering closely with product, finance, data science, and engineering teams. Known for owning technical delivery end-to-end—improving LLM answer relevance and reducing hallucinations, scaling vector search over large document sets, deploying guarded LLM services with monitoring, and accelerating finance reporting and reconciliation through robust ETL and data validation.…AI/ML Engineer with 4+ years of experience in GenAI, machine learning, fraud detection, and financial analytics. I’ve built RAG pipelines, risk-scoring models, ML APIs, and reliable cloud data workflows while partnering closely with product, finance, data science, and engineering teams. Known for owning technical delivery end-to-end—improving LLM answer relevance and reducing hallucinations, scaling vector search over large document sets, deploying guarded LLM services with monitoring, and accelerating finance reporting and reconciliation through robust ETL and data validation.

Available to hire

AI/ML Engineer with 4+ years of experience in GenAI, machine learning, fraud detection, and financial analytics. I’ve built RAG pipelines, risk-scoring models, ML APIs, and reliable cloud data workflows while partnering closely with product, finance, data science, and engineering teams.

Known for owning technical delivery end-to-end—improving LLM answer relevance and reducing hallucinations, scaling vector search over large document sets, deploying guarded LLM services with monitoring, and accelerating finance reporting and reconciliation through robust ETL and data validation.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

AI/ML Engineer at Intuit

August 1, 2025 - Present

Developed RAG pipelines using Python, SQL, LangChain, OpenAI API, AWS, and Snowflake to retrieve finance and tax context for assistant users, improving answer relevance across workflows. Optimized vector search by cleaning, chunking, embedding, indexing, and retrieval across ~22K financial documents, reducing irrelevant results. Built FastAPI services with Docker and MLflow, deployed to AWS, and delivered guarded LLM responses with improved release tracking. Evaluated LLM outputs using metrics such as relevance, accuracy, groundedness, hallucination rate, and consistency, reducing hallucinations across stakeholder review groups.

AI/ML Engineer at Remitly

July 1, 2024 - July 1, 2025

Engineered fraud data ingestion pipelines using Python, SQL, AWS, and Snowflake to consolidate transaction, login, merchant, and device signals for model-ready datasets. Built fraud-risk feature engineering workflows (payment velocity, failed logins, device/location shifts, merchant patterns, prior fraud history) to increase risk-signal coverage. Trained and validated fraud classification models using Scikit-learn, XGBoost, and LightGBM, improving suspicious-activity recall and reducing false positives. Deployed risk-scoring APIs using FastAPI, Docker, MLflow, and AWS to enable real-time scoring, model monitoring, and dashboard visibility for risk and compliance teams.

Data Analyst at TCS

July 1, 2021 - January 1, 2023

Built batch and streaming data pipelines using Python, PySpark, AWS Glue, and Spark Streaming to reduce finance reporting turnaround time and processing delays. Implemented Snowflake warehouse models with SnowSQL tuning and medallion architecture (Bronze/Silver/Gold), improving dashboard load times across finance BI workflows. Designed pipelines using Azure Data Lake/ADLS, Azure Synapse, Azure Databricks, ADF, AWS Glue, and Informatica PowerCenter, improving integration reliability across multiple reporting sources. Automated financial validation, data profiling, and BI dashboards using Pandas, Power BI, Tableau (maintaining ~99.2% accuracy), and supported SAP document validation for migration and reconciliation using SQL and Azure DevOps.

Junior Data Engineer at Infosys

May 1, 2020 - May 1, 2021

Engineered financial reconciliation ETL pipelines using Python, SQL, AWS S3, AWS Glue, and Snowflake to clean finance records and reduce manual validation effort. Structured transaction, invoice, and ledger datasets into Bronze/Silver/Gold Snowflake layers to improve consistency and enable monthly end reviews. Developed Power BI dashboards tracking reconciliation status, missing records, exception trends, and KPIs to support faster finance reviews. Implemented SQL/Pandas data validation rules to detect duplicates, missing records, and mismatches, improving audit readiness for compliance-reviewed datasets.