Este es mi perfilContactar vía CazVidEste perfil está escrito en inglés
Lakshmi
Senior AI/ML Engineer
Contacto
Competencias
Demonstrated experience with Python.
Demonstrated experience with SQL.
Demonstrated experience with Pandas.
Demonstrated experience with NumPy.
Demonstrated experience with ETL.
Educación
Idiomas
Resumen
Senior AI/ML Engineer open to new opportunities
Experiencia
AI/ML Engineer
Developed enterprise AI/ML pipelines using Python, Scikit-learn, XGBoost, PyTorch, Pandas, and NumPy to support predictive modeling, risk analysis, and intelligent decision-making.. Engineered healthcare analytics solutions for claims analysis, member risk stratification, utilization prediction, and identification of patterns across large healthcare datasets.. Developed Generative AI and Retrieval-Augmented Generation (RAG) applications using Claude on Amazon Bedrock, LangChain, embedding models, and vector databases (OpenSearch, FAISS, Pinecone) to enable context-aware retrieval from healthcare documents and enterprise knowledge repositories.. Implemented end-to-end document processing workflows covering ingestion, parsing, chunking, metadata enrichment, embedding generation, semantic search, and context assembly for LLM-based question answering.. Developed cloud-based AI/ML workflows using Amazon SageMaker for model training, evaluation, deployment, and inference, supporting scalable healthcare predictive analytics.. Integrated Amazon Bedrock (Claude) with LLM-powered applications and Amazon S3 document repositories to support Generative AI and Retrieval-Augmented Generation (RAG) workflows.. Developed agentic AI workflows using LangChain and LangGraph, enabling LLM-based agents to coordinate retrieval and multi-step task execution.. Implemented hybrid search and reranking to improve retrieval relevance in RAG pipelines, and evaluated LLM and RAG output quality to measure response accuracy and retrieval performance.. Applied AI guardrails and Responsible AI practices to promote safe, compliant LLM outputs when handling sensitive healthcare information.. Built production-ready Python microservices and inference APIs using FastAPI and REST, integrating machine learning models and LLM-powered capabilities with downstream enterprise applications.. Developed computer vision workflows using Python, OpenCV and PyTorch to preprocess and analyze image-based documents, extracting visual features to support automated document classification and downstream AI processing.. Implemented document ingestion and preprocessing pipelines using Amazon S3 and AWS Lambda, preparing healthcare documents for embedding generation, indexing, and downstream retrieval.. Applied feature engineering, hyperparameter optimization, cross-validation, and model evaluation techniques to improve predictive performance and model generalization.. Established model lifecycle practices using MLflow, Docker, Kubernetes, Git, and CI/CD pipelines for experiment tracking, model versioning, reproducible builds, and controlled deployment.. Implemented automated data-quality checks, API logging, exception handling, and model-performance monitoring to improve reliability and support production troubleshooting.. Collaborated with data engineers, healthcare domain specialists, security teams, and solution architects to translate business requirements into maintainable AI solutions while protecting sensitive healthcare information.
AI/ML Engineer
Developed and optimized supervised machine learning models using Python, Scikit-learn, XGBoost, and LightGBM to support healthcare analytics, patient risk prediction, and utilization analysis.. Processed datasets using Pandas, NumPy, and SQL, implementing data cleansing, feature transformation, missing-value treatment, and validation.. Stored and organized datasets in Amazon S3, establishing structured data zones for raw inputs, transformed datasets, and model-ready features.. Developed serverless data preparation and event-driven processing workflows using AWS Lambda and Amazon S3 events to automate selected ingestion and validation tasks.. Leveraged Amazon SageMaker notebooks and managed training capabilities to experiment with predictive models, compare algorithms, and evaluate model performance.. Built predictive modeling workflows for classification, regression, and risk stratification, comparing algorithms and selecting models based on business objectives and evaluation results.. Developed NLP pipelines to process clinical narratives and documents using text normalization, tokenization, feature extraction, and transformer-based models.. Experimented with deep learning models using TensorFlow for image classification and feature extraction, evaluating model performance with appropriate validation metrics.. Applied pretrained transformer models through Hugging Face Transformers for text classification, semantic representation, and information extraction from unstructured text.. Exposed model predictions through Python-based REST services, enabling integration with analytics platforms and downstream application workflows.. Used Git-based version control, modular Python development, unit testing, and technical documentation to improve maintainability and collaboration across data science and engineering teams.
Machine Learning Engineer
Developed predictive analytics solutions using Python, Scikit-learn, Pandas, and NumPy to identify business trends, classify records, and generate actionable insights from structured datasets.. Built data preparation workflows to consolidate information from relational databases, CSV files, and application sources into consistent, model-ready datasets.. Performed exploratory data analysis, statistical analysis, correlation analysis, and feature selection to identify predictive variables and investigate data quality issues.. Implemented machine learning algorithms including linear regression, logistic regression, decision trees, random forests, and gradient boosting for classification and regression use cases.. Utilized Amazon EC2 to run Python-based data analysis, model development, and batch prediction workloads in configurable cloud compute environments.. Used Amazon S3 to store source datasets, processed files, analytical outputs, and serialized machine learning artifacts for reuse across development workflows.. Developed image-processing utilities using Python and OpenCV to clean, transform, and standardize image inputs for analytical workflows.. Optimized model performance through cross-validation, hyperparameter tuning, feature engineering, and comparison of baseline and advanced models.. Developed reusable Python modules for data transformation, model training, prediction, and evaluation, improving consistency across analytical projects.. Applied natural language processing (NLP) techniques for text preprocessing, feature extraction, and categorization of textual data.
Data Scientist
Built foundational predictive models using Scikit-learn, applying classification and regression techniques to support analytical forecasting and decision-making.. Performed exploratory data analysis, outlier detection, missing-value treatment, data normalization, and categorical encoding to prepare high-quality datasets for modeling.. Analyzed structured datasets using Python, SQL, Pandas, and NumPy to identify trends, patterns, and opportunities for data-driven process improvement.. Applied statistical analysis, correlation testing, and feature engineering to identify meaningful relationships among variables and improve model input quality.. Trained and evaluated models using decision trees, logistic regression, random forests, and other suitable algorithms based on the problem and available data.. Created visualizations using Matplotlib and Seaborn to communicate distributions, trends, model results, and analytical findings to technical and business stakeholders.. Connected Python data processing applications to relational data sources and used AWS IAM permissions to control access to relevant cloud resources.. Configured Amazon CloudWatch logging and basic monitoring for cloud-hosted processing jobs to help identify execution failures and troubleshoot operational issues.. Automated repetitive data extraction, cleaning, aggregation, and validation tasks using Python scripts and reusable analytical functions.
Data Analyst
Developed Python scripts and SQL queries to extract, transform, reconcile, and analyze operational and transactional datasets from relational databases.. Implemented data-quality checks to identify duplicate records, missing values, inconsistent formats, and data discrepancies before reporting and downstream processing.. Used Pandas and NumPy to clean datasets, standardize data types, perform aggregations, and prepare structured inputs for analysis.. Wrote SQL queries using joins, sub queries, grouping, and aggregate functions to combine data from multiple tables and generate business-focused analytical outputs.. Automated recurring data preparation, reconciliation, and reporting tasks using Python, improving repeatability and reducing spreadsheet-based manual work.. Performed exploratory data analysis to identify trends, exceptions, and relationships across key business metrics.. Created charts, summaries, and Excel-based reports to communicate operational performance, data quality findings, and analytical observations to stakeholders.. Supported introductory statistical analysis and predictive modeling initiatives by preparing datasets, engineering basic features, and validating analytical outputs.