Sreevalli

Email: vallisree1925@[Link]
Phone: +1 (605) 400-9843
LinkedIn: [Link]/in/sree-janyavula-1b6b3a83

PROFESSIONAL SUMMARY:

Python Application Engineer with 10+ years of experience designing scalable cloud-native backend systems and AI-driven
enterprise applications. Strong expertise in Generative AI, RAG pipelines, Agentic AI architectures, and LLM orchestration
frameworks. Hands-on experience building multi-agent systems using LangChain, Semantic Kernel, and LlamaIndex. Deep
experience in Azure & GCP cloud architecture, containerized deployments (Docker/Kubernetes), Terraform-based IaC,
and MLOps pipelines
TECHNICAL SKILLS:

Programming Languages Python (3.6/3.7), PySpark, Bash,

Generative AI Generative AI, Agentic AI, RAG, Prompt Engineering, Multi-Agent Systems
AI Frameworks & Vector Lang Chain , Lang Graph , Semantic Kernel, Azure OpenAI
Databases
Cloud Platforms AWS (Primary), Google Cloud Platform (GCP)
AWS Services Lambda, EC2, S3, Elastic Beanstalk, ECS, EKS
Backend Frameworks Django, Fast API
DevOps & CI/CD Terraform, Jenkins, Docker, Kubernetes
IDE / Development Tools Visual Studio Code (VS Code), PyCharm
Database Technologies MySQL, PL/SQL, Big Query
Data Processing ETL/ELT, Kafka, Pub/Sub, Data Streaming

EDUCATION:

• Master of Science in “Data Analytics and Business Statistics Program” from New England College – Henniker, NH in
Dec 2020
• Related Courses: Applied Business Statistics I, Applied Business Statistics II, Cloud Computing, Database Design,
Database Management, Data Mining for the intel Business, Information Security, IT Project Management and Net-
work communication.

PROFESSIONAL EXPERIENCE:

Client: Optum Serve, (CMS) (Remote) Feb 2022 - Present

Role: Lead Python Developer

Responsibilities:
• Implemented strategic enhancements to SaaS reports, contributing to improved data visualization and reporting
capabilities.
• Developed Python-based data ingestion and transformation pipelines using Snowflake as a cloud data warehouse.
• Designed and implemented enterprise RAG architecture using Azure OpenAI and vector databases to enable
intelligent document retrieval across healthcare compliance datasets
• Designed and optimized Snowflake data models and SQL queries for large-scale healthcare datasets.
• Built multi-agent AI workflows using LangChain and Semantic Kernel to automate CMS reporting and audit workflows
• Implemented memory management strategies for AI agents using vector embeddings and contextual storage
• Implemented CI/CD pipelines using GitHub Actions for automated build and deployment.
• Demonstrated adaptability by delivering impactful solutions in diverse data environments, showcasing versatility in
addressing evolving project requirements.
• Design, develop, and maintain scalable backend services using AWS technologies, ensuring optimal performance and
reliability.
• Developed and debugged Python applications using Visual Studio Code (VS Code).
• Designed guardrails and validation layers for safe AI response generation in healthcare-sensitive systems (HIPAA
compliant)
• Developed automated ETL/ELT pipelines using Data Prep and orchestrated tasks using Google Cloud Composer and
Apache Airflow.
• Optimized backend services to support large-scale retail operations, ensuring minimal downtime.
• Developed AI orchestration pipelines coordinating multiple agents for goal-based task execution
• Conducted unit and integration testing to ensure robust application performance.
• Built ETL pipelines using Talend and Control-M to process multi-terabyte datasets across multiple platforms.
• Developed Python-based data validation and transformation scripts to streamline GCS to Big Query workflows.
• Implemented GCP Composer workflows to schedule and monitor data integration processes.

Environment: Python 3.9+, Fast API, Azure OpenAI, LangChain, Semantic Kernel, Pinecone, Azure AI Search, GCP, Docker,
Kubernetes, Terraform, CI/CD, OAuth2, RBAC, Kafka
Client: Apple, Austin, Texas Feb 2021 – Feb 2022
Role: Backend Python Developer

Responsibilities:
• Involved in the software development lifecycle (SDLC) of tracking the requirements, gathering, analysis, detailed
design, development, system testing and user acceptance testing.
• Developed monitoring and notification tools using Python.
• Developed and maintained PL/SQL stored procedures, packages, functions, and triggers to support backend business
logic and high-volume transactional systems.
• Implemented enterprise job orchestration using Control-M scheduling tools.
• Integrated LLM services with enterprise APIs for intelligent forecasting workflows
• Develop, test, and deploy Python applications and microservices in AWS environments using AWS Elastic Beanstalk,
ECS, and EKS.
• Worked closely with DBAs to perform Oracle performance tuning, query optimization, and database monitoring in
production environments.
• Implemented bulk data processing using PL/SQL features such as BULK COLLECT and FORALL to handle large-scale
data operations.
• Worked with Product Planning and Forecast team to build Django applications.
• Worked on Django API's for accessing the database.
• Built evaluation metrics to measure LLM accuracy and reasoning quality
• Provide a high level of technical support, perform root cause analysis for problems experienced within the area of
DataStage ETL Jobs
• Performed Oracle SQL query optimization, indexing strategies, and execution plan analysis to improve database
performance for large datasets.
• Troubleshoot and resolve issues related to AWS services and Python-based applications, ensuring minimal
downtime.
• Experience in writing complex SQL in relational databases
• Designed and developed communication between client and server using Secured Web services/ APIs.

Environment: Python 3.6/3.7, Django 2.2.0, MySQL, PL/SQL, Shell Script, HTML, SQL, Bootstrap, web
Scraping, DataStage’s, PyCharm, Fast API.

Client: Thames water, India Oct 2012 – Sep 2018

Role: Python Developer

Responsibilities:
• Involved in all phases of SDLC including Requirement Gathering, Design, Analysis and Testing of customer
specifications, Development, and Deployment of the Application.
• Developed entire frontend and backend modules using Python on Django Web Framework.
• Developed views and templates with Python and Django's view controller and templating language to create a user-
friendly interface using MVC architecture.
• Collaborate with the DevOps team to integrate backend services with CI/CD pipelines, utilizing AWS Code Pipeline
and Code Build.
• Responsible for creating visually appealing web pages with Bootstrap and HTML5.
• Used server-side authentication and cookie-based session management to secure information and allow for
persistence of data.
• Implement real-time data processing solutions using AWS Kinesis and AWS DynamoDB to support high-throughput
applications.
• Collaborated within a team using an Agile Development workflow and widely accepted collaboration practices using
Git.

Environment: Python, Django, JavaScript, MySQL, NumPy, SciPy, Pandas API, PEP, PIP, Jenkins, JSON, Git, JavaScript, AJAX,
RESTful webservice, MySQL, PyUnit.

ACHIEVEMENTS:

• Certified as Scrum Master.

• CMS background clearance check done.
• AWS cloud certified

PROJECTS:

• Real-Time Data Streaming Platform:

Built a scalable data streaming solution using Kafka, Pub/Sub, and PySpark to process real-time data feeds for a
financial analytics platform.
• Data Warehouse Modernization:
Migrated on-premises data warehouses to Big Query, improving query speeds by 40% and reducing infrastructure
costs by 25%.
• ETL Pipeline Automation:
Designed ETL workflows using Apache Airflow, automating data ingestion and transformation for a healthcare
provider’s analytics needs.