AI/ML Engineer with 8+ Years of Experience

Likitha

AI/ML Engineer

***********@*****.*** 214-***-****

SUMMARY

Dedicated AI/ML Engineer and Data Science professional with 8+ years of experience building, deploying, and improving machine learning solutions that support analytics and automation.

Experienced in computer vision using OpenCV and YOLO for detection, segmentation, tracking, and real-time image processing.

Skilled in designing deep learning models using TensorFlow and PyTorch, applying CNN, RNN, and LSTM networks to vision, sequence, and pattern-recognition tasks.

Capable of building reliable data pipelines and ETL processes using Apache Spark, Hadoop, and cloud-native tools across AWS and Azure.

Adaptable in Agile teams, contributing to structured planning, effective communication, and steady sprint progress.

Knowledgeable in statistical modeling, A/B testing, and parameter optimization with Optuna, supported by strong use of Pandas and NumPy.

Hands-on in MLOps practices, automating training, packaging, and deployment with Docker, CI/CD pipelines, AWS Lambda, and AWS Glue.

Analytical in problem-solving, delivering solutions that align with practical business needs and technical goals.

Seasoned in NLP using Hugging Face Transformers and SpaCy, creating scalable pipelines for entity extraction, text classification, and semantic analysis.

Versed in managing SQL-based databases and integrating systems using Kafka, REST APIs, and event-driven architectures.

Comfortable translating analytical outcomes into clear insights through dashboards in Power BI, Tableau, and Jupyter.

Proficient in Reinforcement Learning, XGBoost, and Faster R-CNN for predictive modeling, adaptive systems, and image-driven decision workflows.

IT SKILLS

Machine Learning & Generative AI: Generative AI, GPT models, Reinforcement Learning, XGBoost, Faster R-CNN, YOLO, CNNs, RNNs, LSTMs, Transformers, TensorFlow, PyTorch, Hugging Face

NLP & Text Analytics: NER, Sentiment Analysis, Text Classification, Topic Modeling, Language Modeling, Seq2Seq, SpaCy, NLTK

Data Science & Statistics: Predictive Analytics, Classification, Regression, Clustering, A/B Testing, Time Series, Bayesian Methods, EDA, Feature Engineering, Optuna, Pandas, NumPy

Cloud & MLOps: AWS Lambda, AWS Glue, Step Functions, Azure Cognitive Services, Docker, CI/CD, Flask/TensorFlow deployment, Model Tracking & Monitoring

Big Data & Databases: Apache Spark, Hadoop, ETL, Snowflake, MySQL, SQL Server, Azure Synapse, ADF, SQL

Programming & Integration: Python, SQL, JavaScript, Flask, REST APIs, Kafka, Web Services

Visualization & Collaboration: Power BI, Tableau, Jupyter, Google Sheets, Git, Agile/Scrum, Confluence

Computer Vision: OpenCV, YOLO, Image Classification, Object Detection, Image Segmentation

PROFESSIONAL EXPERIENCE

Amboy Bank, Old Bridge, NJ September 2024 - Present

AI/ML Engineer (Data Science)

Constructed scalable TensorFlow and Flask solutions, supported by TensorFlow Serving for versioning, rollouts, and stable production releases.

Used SHAP, LIME, and related tools to deliver interpretable results and strengthen model transparency.

Developed computer-vision models with OpenCV, CNNs, and RNNs for detection, tracking, and feature extraction.

Applied fairness checks, bias controls, and interpretability techniques throughout the ML lifecycle to support responsible modeling.

Leveraged XGBoost for predictive analytics, feature selection, and structured classification and regression tasks.

Applied Faster R-CNN for high-accuracy object detection within real-time and dynamic vision environments.

Integrated vector databases and embedding retrieval pipelines to power semantic search and LLM-aligned tasks.

Explored reinforcement-learning methods to improve decision policies and enhance adaptive behaviors in automated systems.

Maintained monitoring dashboards, logging, and drift-detection systems to ensure long-term model reliability.

Implemented GPT-based generative models for sentiment analysis, text generation, and conversational workflows to strengthen user interaction and automation.

Developed NLP pipelines for intent detection, NER, and text classification using SpaCy, NLTK, Transformers, and sequence-to-sequence modeling.

Integrated feature stores to strengthen training-serving consistency and feature versioning across ML workflows.

Refined model performance using Optuna for hyperparameter tuning and MLflow for experiment tracking, metrics, and reproducibility.

Utilized Apache Spark and Hadoop for large-scale data processing, distributed analytics, and scalable training.

Published ML and NLP models as RESTful APIs, enabling smooth integration with enterprise applications and microservice architectures.

Used Kafka event streams to support real-time inference, message processing, and continuous data ingestion.

Optimized MLOps workflows with AWS Lambda, Glue, and Step Functions to automate training and deployment.

Collaborated within Agile and Scrum teams to deliver machine-learning solutions through iterative planning, refinement, and cross-team coordination.

Environment: Generative AI, Python, TensorFlow, PyTorch, TensorFlow Serving, GPT, Flask, Spark, Hadoop, Kafka, AWS (Lambda, Glue, Step Functions), Microservices, Real-time Processing, XGBoost, CNNs, RNNs, OpenCV, SpaCy, NLTK, MLflow, Optuna, Feature Stores, Vector Databases, Model Monitoring, Drift Detection, Agile, Scrum

Encompass Health, Birmingham, AL June 2023 - August 2024

Machine Learning Engineer (Data Science)

Adopted MLflow for experiment tracking and model version control across iterative experiments.

Applied MLOps practices by setting up CI/CD pipelines for deployment, evaluation, and continuous retraining.

Used feature stores to maintain consistency between training and serving features in production workflows.

Ran predictive analyses to uncover trends, support forecasting, and guide strategic decisions.

Deployed YOLO-based object detection pipelines for real-time recognition in fast-changing environments.

Developed deep learning models in PyTorch using CNNs, LSTMs, and Transformers to strengthen both vision and language-based predictions.

Leveraged Azure Cognitive Services and Azure OpenAI to support NLP automation, text analytics, and cognitive processing tasks.

Handled high-volume datasets using Pandas and NumPy, improving data quality through targeted wrangling and feature engineering.

Designed Power BI dashboards to communicate analytical outcomes and support business planning.

Delivered low-latency inference through REST APIs, enabling real-time responses for production workloads.

Enhanced accuracy through hyperparameter tuning with Optuna, improving forecasting and analytical models.

Applied supervised and unsupervised learning to identify behaviors, clusters, and hidden patterns in data.

Validated model performance using A/B testing, ensuring reliability and statistical consistency.

Built scalable data integration pipelines with Azure Synapse, ADF, and SQL Server to support enterprise analytics.

Integrated vector search systems to support embedding-based retrieval and semantic matching use cases.

Tracked drift indicators and performance signals to adjust training workflows and maintain model stability.

Developed classification, regression, and clustering models to generate insights across diverse datasets.

Utilized Spark and Hadoop for distributed processing and large-scale feature preparation.

Environment: Python, PyTorch, TensorFlow, CNN/LSTM/Transformer models, YOLO, Pandas, NumPy, Optuna, MLflow, REST APIs, Azure (Cognitive Services, OpenAI, Synapse, ADF), SQL Server, Spark, Hadoop, Feature Stores, Vector Search, MLOps/CI/CD, Power BI

F&G (Fidelity & Guaranty Life), Des Moines, IA April 2022 - May 2023

Data Scientist

Automated recurring analysis and reporting processes through Jupyter Notebooks to speed up insight delivery.

Leveraged feature engineering and exploratory analysis to uncover patterns and refine model readiness.

Applied NLP and sentiment analysis to extract insights from customer feedback, reviews, and social media.

Executed real-time and big data workflows using Apache Spark and Hadoop to support scalable analytics.

Applied model evaluation techniques such as cross-validation and error analysis to ensure consistent performance.

Designed Tableau and Power BI dashboards to present results that aligned with business priorities.

Used Bayesian inference, probability techniques, and statistical tests to validate results and support conclusions.

Integrated APIs and automated data flows to enhance accessibility and streamline operations across systems.

Handled large datasets with Python, Pandas, and NumPy to improve data quality and speed up preparation tasks.

Performed time series forecasting to support demand planning, trend analysis, and strategic decision-making.

Optimized SQL queries in Snowflake and MySQL to boost reporting efficiency and maintain reliable model inputs.

Collaborated with cross-functional teams to integrate data-driven recommendations into business workflows.

Developed classification, regression, and clustering models using Scikit-Learn to strengthen predictive accuracy.

Environment: Apache Spark, Hadoop, Python (Pandas, NumPy, Scikit-Learn), Jupyter Notebooks, Snowflake, MySQL, NLP, APIs, Tableau, Power BI

iPrism Technologies, India July 2017 - March 2022

Data Analyst

Utilized Google Sheets for real-time validation, automated reporting tasks, and quick ad hoc evaluations.

Supported data governance by maintaining consistent naming standards, business rules, and validation checks.

Executed ETL workflows to gather, organize, and prepare data from multiple systems for downstream analysis.

Applied descriptive statistics, probability methods, and hypothesis testing to guide strategic planning and performance reviews.

Extracted and analyzed large datasets using SQL to enable accurate reporting and informed decision-making.

Created dashboards and reports in Excel and Google Sheets to track KPIs and communicate insights clearly.

Improved data quality by identifying outliers, addressing missing values, and removing duplicates to maintain dataset consistency.

Performed detailed Excel analysis using VLOOKUP, PivotTables, and Conditional Formatting to uncover trends for cross-functional groups.

Documented workflows, processes, and data dictionaries in Confluence to support clarity and knowledge sharing.

Automated data cleaning, transformation, and exploratory analysis in Python with Pandas and NumPy to improve efficiency and reliability.

Collaborated with product and marketing teams to design and assess A/B tests that supported engagement and conversion improvements.

Environment: SQL, Python (Pandas, NumPy), ETL, A/B Testing, Descriptive Statistics, Excel (VLOOKUP, PivotTables, Charts), Google Sheets, Confluence

ACADEMIC DETAILS

Bachelor of Technology (B.Tech), Computer Science and Engineering (CSE), LITS, India.

Contact this candidate