Surender Guthula

[email protected] | (678) 551-2627 | LinkedIn

Professional Summary
16+ years of experience as an AI/ML & Python Developer, specializing in designing and developing cloud-native
applications using Python, Java, and AWS across enterprise-scale systems.Leading full lifecycle AWS Lambda
development, including design, coding, unit testing, deployment, and performance optimization in production
environments.Deep hands-on expertise in integrating Python-based Lambdas with Java backend services using
REST APIs and asynchronous Kafka/SNS messaging.Proficient with AWS SDK (Boto3), AWS SAM, and
CloudFormation for resource orchestration and automation.Skilled in leveraging AI-assisted tools (Amazon Q,
GitHub Copilot, ChatGPT) to accelerate coding, improve test coverage, and optimize application
performance.Deep hands-on experience in integrating Python-based AWS Lambdas with Java backend services
through REST and asynchronous messaging (Kafka, SNS). Strong command of AWS SDK (Boto3) for automation
of deployments, resource provisioning, and service orchestration.Leveraging AI-assisted tools like Amazon Q
and GitHub Copilot to accelerate code generation, improve test coverage, and optimize Lambda
performance.Strong programming skills in Python, R, and SQL, and a deep understanding of AI/ML algorithms,
statistical modeling, and data visualization. Passionate about solving complex problems through data-driven
insights and cutting-edge technologies.

TECHNICAL SKILLS
● Programming & Frameworks: Python (Flask, FastAPI, NumPy, Pandas, Boto3), Java (Spring Boot, JAX-RS), SQL, Scala,
C++
● Machine Learning & AI: Supervised Learning (Regression, Decision Trees, Random Forests, XGBoost, Gradient
Boosting), Unsupervised Learning (K-Means, PCA, Hierarchical Clustering), NLP (Text Classification, Named Entity
Recognition, Sentiment Analysis, BERT, Transformer models, spaCy), Deep Learning (CNNs, RNNs, GANs),
Reinforcement Learning
● Big Data & Data Engineering: Hadoop, Hive, MapReduce, Apache Kafka, AWS Glue, GCP Dataflow, Redshift,
PostgreSQL, SQL Server, Snowflake
● Messaging & Streaming: Apache Kafka, Amazon SNS/SQS, Kinesis, EventBridge

● Cloud Platforms: AWS (Lambda, EC2, API Gateway, SNS, SQS, CloudWatch, Glue, Step Functions), Azure, GCP

● AWS Development: AWS Lambda (Full SDLC), Boto3, CloudFormation, AWS SAM, Step Functions

● Visualization & Analytics: Tableau, Power BI, Looker, Matplotlib, Seaborn

● MLOps, DevOps & Deployment: Docker, Jenkins, Kubernetes, Git, Bitbucket, CI/CD Pipelines, MLflow, Airflow,
FastAPI, Auto-scaling, Monitoring Tools (GCP Monitoring, AWS CloudWatch)
● Build Tools: Maven, Gradle (for Java integration)

● Advanced Techniques & Explainability: SHAP, LIME, Autoencoders, Anomaly Detection, Time-Series Forecasting
(Prophet, ARIMA), Fraud Detection Models, Computer Vision for Quality Control
● AI & Automation Tools: Amazon Q, GitHub Copilot, ChatGPT — for intelligent code completion, testing, and
refactoring

Education
• University of Maryland Eastern Shore (UMES), MD, USA
M.S., Applied Computer Science

• SBMSIT (VTU), Bangalore, India

PROFESSIONAL EXPERIENCE
AI/ML & Python Developer
RetailMeNot, TX Sep 2023 – Present

● Designed and developed scalable AI-powered Python applications and AWS Lambda-based microservices,
delivering personalized recommendations based on real-time user data and purchase history
● Leading full-lifecycle development of AWS Lambda–based microservices written in Python for real-time deal
processing and user recommendation workflows.
● Designed and implemented RESTful APIs integrating Python AWS Lambdas with Java Spring Boot backend
services.
● Developed Kafka-driven event processing pipelines for asynchronous messaging between distributed systems.

● Built serverless applications on AWS using Lambda, API Gateway, Step Functions, and DynamoDB for scalable
data flow.
● Refactored legacy Java monolith APIs into lightweight, modular Python AWS Lambda functions to enhance
scalability and reduce latency.
● Utilized AWS SDK (Boto3) for automation of deployments, monitoring, and configuration management of
Lambda resources.
● Created custom Java SDK wrappers to integrate with existing enterprise APIs and cloud connectors.

● Leveraged Amazon Q and GitHub Copilot to accelerate code generation, automate documentation, and enforce
best practices.
● Implemented end-to-end SDLC for serverless applications including build, test, deploy, and performance
optimization.
● Developed data transformation and validation layers using Python for ingestion pipelines from S3 to Redshift.

● Used AWS CloudFormation and SAM templates for IaC-based provisioning of serverless environments.

● Integrated Java microservices with Python Lambdas via Kafka topics and SQS queues, ensuring reliable event
delivery.
● Designed API Gateway routes with Python Lambda handlers for high-availability customer data endpoints.

● Configured CloudWatch metrics, logs, and alarms for proactive application monitoring and alerting.

● Built test automation frameworks in Python (PyTest) and Java (JUnit) for Lambda and API regression suites.

● Implemented CORS, OAuth2, and JWT-based authentication for secure cross-platform API access.

● Optimized Lambda cold-start performance using provisioned concurrency and dependency trimming.

● Participated in Agile sprint cycles, contributing to backlog grooming, code reviews, and architecture discussions.

● Collaborated with DevOps teams to integrate CI/CD pipelines using Jenkins and AWS CodePipeline for
automated deployments.
● Delivered high-performance serverless applications meeting enterprise compliance standards and achieving 30%
faster execution times.
 Environment: Python, Java (Spring Boot), AWS (Lambda, API Gateway, CloudFormation, SNS, SQS, Step Functions,
CloudWatch, Boto3), Apache Kafka, Jenkins, Git, FastAPI, Looker, Amazon Q, GitHub Copilot, Airflow

Senior Python & AWS Developer

● Designed and deployed an ML-based Medicaid fraud detection system, reducing fraudulent claims and
improving financial oversight.
● Designed and implemented Python- and Java-based AWS Lambda applications supporting Medicaid fraud
detection and claims validation.
● Developed asynchronous event-driven services using Kafka topics, SQS, and SNS for data ingestion and real-time
alerts.
● Built RESTful APIs in FastAPI (Python) and Spring Boot (Java) to enable hybrid microservice communication across
AWS.
● Re-engineered existing Java batch jobs into Python Lambda functions, reducing execution cost and runtime by
35%.
● Created automated AWS Glue pipelines for data preprocessing, cleansing, and ETL transformation.

● Integrated Python and Java modules into unified AWS architectures with Lambda triggers and API Gateway
endpoints.
● Utilized AWS Boto3 and CloudFormation for automation of Lambda provisioning and environment configuration.

● Implemented Kafka message consumers and producers for streaming transactional data between microservices.

● Developed serverless data enrichment workflows leveraging AWS Glue, Redshift, and Lambda for scalable
analytics.
● Employed Amazon Q and GitHub Copilot to boost development efficiency and ensure consistent code quality.

● Built CI/CD pipelines using Jenkins and Bitbucket, integrating build, test, and deploy stages for Lambda and Java
components.
● Monitored application performance using AWS CloudWatch, X-Ray, and Lambda insights dashboards.

● Implemented error handling, retries, and DLQ logic in Python Lambdas for resilient distributed processing.

● Designed custom event schemas for Kafka integration between Python and Java services.

● Created unit and integration test suites using PyTest, JUnit, and Moto for AWS mocking.

● Collaborated with business analysts and architects to implement microservices-based designs following domain-
driven principles.
● Documented API specifications and integrated with Postman collections for cross-team collaboration.

● Conducted security reviews ensuring IAM roles, encryption, and data access policies complied with HIPAA
guidelines.
● Led modernization of data systems by migrating on-prem Java apps to AWS serverless architectures using
Python.
● Mentored developers on AWS Lambda optimization, Python coding standards, and Kafka message design
patterns.

Environment: Python, Java (Spring Boot), AWS (Lambda, Glue, Redshift, CloudFormation, Boto3, API Gateway,
CloudWatch, SQS, SNS), Apache Kafka, Jenkins, Bitbucket, FastAPI, Amazon Q, GitHub Copilot, PostgreSQL, Airflow

Data Scientist
Sailpoint, TX Oct 2011 – Apr 2018

● Built scalable ETL workflows on AWS using Redshift, EC2, and Python-based automation, improving data
processing efficiency by 40%.

● Developed predictive maintenance models with Scikit-learn and XGBoost, reducing equipment downtime
by 25%.

● Applied K-Means clustering to segment customer behavior and improve targeted marketing campaigns.

● Designed and deployed Flask-based REST APIs to integrate ML models into SailPoint’s data ecosystem in real
time.

● Automated time-series forecasting for supply chain optimization, achieving a 15% reduction in inventory costs.

● Created Power BI dashboards (introduced mid-2010s) to visualize operational performance metrics and KPIs.

● Engineered key features and tuned gradient-boosted models (GBMs), improving fraud and performance
predictions by 20%.

● Implemented NLP models (using NLTK and Scikit-learn) for document classification, automating compliance
workflows.

● Migrated on-premises data warehouses to AWS Redshift, resulting in cost savings and improved scalability.

● Built anomaly detection models to identify inefficiencies in manufacturing and operational datasets.

● Conducted root cause analysis to resolve data discrepancies in large-scale datasets.

● Developed data pipelines to preprocess IoT sensor data, improving equipment failure prediction accuracy
by 30%.

● Collaborated with DevOps teams to establish CI/CD pipelines for model deployment using Jenkins and Git,
reducing update time and model downtime.

● Applied feature importance and partial dependency analysis to explain model decisions during regulatory
audits (precursor to modern XAI).

● Performed time-series analysis on telemetry data to detect early signs of wear and optimize maintenance
schedules.

● Mentored junior engineers and analysts on machine learning algorithms, feature engineering, and statistical
modeling.
● Migrated legacy Java modules into Python-based microservices deployed as AWS Lambdas, reducing
infrastructure overhead by 35%.

● Developed Kafka-based event streaming between Java data services and Python APIs for near real-time
synchronization.

● Implemented AWS CI/CD pipeline using Jenkins and CodePipeline to deploy Lambda-based analytics services.

● Conducted sentiment analysis on employee survey data to provide actionable insights for HR teams.

● Automated data validation and quality checks to reduce critical workflow errors by 35%.
Environment: Python, Scikit-learn, XGBoost, Flask, AWS (EC2, Redshift, S3), Power BI, K-Means, Gradient-Boosted
Machines (GBMs), Jenkins, Git, Airflow (introduced 2015), PostgreSQL, NLTK, Time-Series Forecasting, Anomaly
Detection
Data Scientist
MedeAnalytics, TX Aug 2007 – Oct 2011

● Performed exploratory data analysis (EDA) on healthcare and financial datasets using Python (pandas,
NumPy) and SQL, identifying key trends to support data-driven business decisions.

● Built predictive models using logistic regression, decision trees, and clustering (K-Means) to forecast patient
utilization patterns and improve service efficiency.

● Applied statistical hypothesis testing and correlation analysis to detect anomalies and outliers in transactional
datasets.

● Developed time-series forecasting models to predict operational metrics such as claim volume and customer
churn, enhancing resource planning accuracy.

● Created data visualizations and performance dashboards using Tableau/QlikView, translating analytical results
into actionable insights for executives.

● Developed and deployed Python-based AWS Lambdas to automate data validation and ETL workflows,
integrating outputs with Java analytics components.

● Collaborated with cross-functional teams to define key performance indicators (KPIs) and analytical
methodologies aligned with business goals.

● Designed and implemented data preprocessing workflows to clean and normalize structured and semi-
structured data from multiple sources.

● Conducted segmentation analysis to classify customers based on behavior and demographics, driving targeted
marketing and improving ROI by 15%.

● Assisted data engineers in migrating datasets to Hadoop and Hive, enabling scalable analytics for large historical
data archives.

● Used Python scripting for automation of repetitive data analysis tasks, reducing manual processing time by 40%.

● Generated statistical reports and communicated insights to stakeholders, influencing strategic decision-making
in risk assessment and compliance.

● Conducted root cause analysis for data inconsistencies and ensured data accuracy through validation checks.
● Supported the creation of metadata documentation to ensure transparency, traceability, and consistency in
analytical workflows.

● Mentored junior analysts on data modeling, feature engineering, and best practices for reproducible research
and reporting.
Environment: Python (NumPy, pandas, SciPy), SQL, Hadoop, Hive, MapReduce, Tableau, PostgreSQL, SQL Server, R, ETL
Pipelines, Data Validation, Metadata Management