Priyanka Ponnam
Summary
Innovative Artificial Intelligence Engineer adept at delivering high-value projects with speed and accuracy. Skilled in machine learning, natural language processing, and algorithm development. Excel in problem-solving, critical thinking, and effective communication to navigate complex challenges and collaborate across teams for optimal outcomes.
Overview
11
11
years of professional experience
Work History
Cloud AI Engineer
JPMorgan Chase
02.2024 - Current
- Utilized Agile methodology for software development, encompassing problem definition, requirement gathering, iterative development, business modeling, and communication with technical teams.
- Designed and implemented ETL workflows using Talend to extract, transform, and load large datasets from multiple sources into data warehouses, improving data availability and accuracy for analytics.
- Architected agentic workflows using the Agno framework to orchestrate multi-model LLM interactions, enabling autonomous decision-making in complex data transformation tasks.
- Built notification systems using AWS SNS, integrating with other AWS services to send alerts, updates, and operational data to end-users or systems.
- Optimized AWS SQS message retention, dead-letter queues, and visibility timeouts to improve system reliability and ensure high availability of services.
- Implemented AWS Bedrock for rapidly building and deploying AI models, enhancing customer interactions and automating content generation tasks.
- Used terraform to deploy AWS services, developed terraform code for modules and resources.
- Developed specialized AI Agents with Agno to automate the monitoring of CI/CD pipelines, reducing manual intervention for deployment bottleneck identification by 40%.
- Built intelligent assistants using Agno's multi-modal capabilities to process both text-based queries and uploaded financial document images (PDFs/Invoices), leveraging Gemini 2.5 Pro for high-accuracy extraction.
- Designed and implemented ETL workflows using Talend to extract, transform, and load large datasets, including financial data from SAP ERP systems, into data warehouses, improving data availability and accuracy for analytics.
- Collaborated with ML engineers and data scientists to build AI-powered solutions, including conversational chatbots, RAG pipelines, and embedding workflows using AWS GenAI tools such as Amazon Bedrock, Titan models, SageMaker JumpStart, and SageMaker Pipelines.
- Designed Retrieval-Augmented Generation (RAG) frameworks combining Amazon Kendra for semantic search with Bedrock-hosted large language models (LLMs) for dynamic response generation.
- Integrated Splunk into GenAI document retrieval pipelines to monitor vector ingestion, API latency, and semantic search performance, enabling root-cause analysis of LLM response delays at different stages of vector lookup.
- Engineered and managed scalable data pipelines that power RAG-based conversational AI, delivering real-time contextual responses enriched with external knowledge.
- Built chatbot solutions combining Amazon Lex, Comprehend, and Bedrock to deliver intelligent, multilingual, and context-aware conversational experiences.
- Developed embedding pipelines and vector feature stores using SageMaker with FAISS, optimizing semantic search performance for structured and unstructured datasets.
- Architected and implemented data pipelines supporting GenAI and ML platforms, enabling seamless integration of generative models into business workflows.
- Designed and implemented comprehensive reports and interactive dashboards utilizing AWS S3, Lambda, Athena, and QuickSight to visualize metrics, usage patterns, trends, and user behaviors.
- Leveraged AWS DMS (Database Migration Service) for seamless migration of on-premises databases to AWS RDS and Amazon Redshift, ensuring data accuracy and consistency.
- Integrated AWS ECS with AWS RDS and S3 for seamless data storage and retrieval, ensuring high availability and optimized resource utilization.
- Developed data processing solutions using PySpark and Spark SQL to enable faster testing, transformation, and analysis of large datasets.
- Built Spark applications to consume streaming data from Apache Kafka, supporting real-time processing workflows.
- Utilized Spark and Spark SQL to read Parquet files and dynamically create Hive tables using the Scala API for optimized storage and querying.
- Designed and deployed containerized applications using Amazon ECS, ensuring scalability and efficient resource utilization.
Data Engineer
Bank of America
09.2021 - 02.2023
- Collaborated on building reliable big data infrastructure using Spark and container services.
- Developed and optimized data processing pipelines in Spark for analytics.
- Deployed and managed Snowflake data warehousing solutions on GCP Cloud. Designed optimized data models in Snowflake for scalability.
- Utilized GCP services like BigQuery, Dataflow, Pub/Sub, and Cloud Storage for data processing. Integrated GCP services for seamless data storage, retrieval, and real-time processing.
- Proficient in Databricks for data engineering tasks and workflow optimization.
- Implemented data transformations and models using DBT for structured datasets.
- Used Terraform for deploying GCP services and infrastructure.
- Implemented CI/CD pipelines for automated deployment processes.
- Collaborated with security teams for data policy compliance and retention models. Implemented data safeguarding measures using GCP's Data Loss Prevention (DLP).
- Centralized and analyzed logs using Google Cloud Logging.
- Implemented monitoring solutions for GCP services using CloudWatch and relevant tools.
- Extensive knowledge in Vector Embeddings and Generative AI Data Engineer Services, including Document AI, Vector AI, Cloud Storage, and AlloyDB.
- Utilized GCP services like Document AI with different parsers for extracting data from PDF files.
- Leveraged Document AI's pre-trained models for automatic text extraction, classification, and entity recognition, enabling rapid processing of large volumes of documents.
- Used Vector AI with embedding models to generate embedding vectors for the extracted text.
- Integrated Vertex AI with other GCP services like BigQuery and Cloud Storage for seamless data processing and analysis, creating powerful AI-driven solutions for business intelligence.
- Integrated AlloyDB for loading embedding vectors for faster retrieval and data processing.
- Having Good knowledge in Llama Index and Gemini AI for prompt engineering.
- Used Cloud functions, Cloud pub-sub and BigQuery to build streamline dashboard to monitor services.
- Created jobs using Cloud composer (Airflow DAG) to migrate data from Data Lake (cloud storage) to transform it using DataProc and ingest in BigQuery for further analysis.
- Built batch and streaming jobs using GCP Services like BigQuery, Pub/Sub, DataProc, Dataflow, CloudRun, Compute engine and Cloud Composer.
Big Data Engineer
S&P Global Market Intelligence
09.2017 - 08.2021
- Collaborated with business, analytical teams, and data scientist to improve efficiency, increase the applicability of predictive models, and help translate ad-hoc analyses into scalable data delivery solutions.
- Collaborated with DevOps team to integrate innovations and algorithms into a production system.
- Worked with the DevOps team to create and manage deployment workflows for all scripts and code.
- Develop and maintained scalable data pipelines that will ingest, transform, and distribute data streams and batches within the AWS S3 and Snowflake using AWS Step Function, AWS Lambda, AWS Kinesis, AWS Glue and AWS EMR.
- Created batch pipelines using AWS S3, AWS Lambda, AWS Glue, AWS EMR, AWS Athena, AWS RedShift, AWS RDS etc.
- Used AWS services like AWS S3, AWS RDS and AWS Redshift for storage.
- Created Apache Airflow dags to ingest data from sources like API's, Servers, and Databases to transform using PySpark in Glue and EMR and loaded data into Data Warehouse like AWS RedShift.
- Created Data pipelines using AWS services like S3, Glue, EMR, Lambda, Athena, IAM, etc.
- Created reports and dashboards that provide information on metrics, usage, trends, and behaviors using AWS services like S3, Lambda, Athena and QuickSight.
- Orchestrated pipelines and dataflow using Apache Airflow and Step Function.
- Created reports and dashboards using AWS services like Lambda, Glue, Step Function and QuickSight.
- Created monitoring service using AWS CloudWatch, AWS Lambda, AWS Glue, AWS Step Function, Grafana and ElasticSearch.
- Created Airflow dags to extract, transform and load data into Data Warehouse.
- Developed and deployed Kubernetes pods to extract, transform and load data.
- Used Docker and Kubernetes for Data Pipelines and ETL Pipelines.
- Used Hadoop ecosystems like Apache HDFS, Apache Spark, Apache Hive, Apache Airflow and Apache Kafka
- Facilitated the developed and deployed proof-of-concept machine learning systems.
Data Analyst
HP
01.2016 - 08.2017
- Gathered, cleaned, and transformed raw data from multiple sources (databases, APIs, flat files) for analysis.
- Developed and automated reports, dashboards, and visualizations using tools like Power BI / Tableau / Google Data Studio / Looker.
- Performed exploratory data analysis (EDA) to identify patterns, trends, and anomalies.
- Wrote complex SQL queries to extract, manipulate, and analyze large datasets from relational databases (e.g., PostgreSQL, MySQL, Redshift, BigQuery).
- Collaborated with business users to define KPIs and metrics for performance tracking.
- Built predictive and descriptive models in collaboration with data science teams.
- Conducted A/B testing and statistical analysis to support marketing and product decisions.
- Automated recurring data tasks and reports using Python, R, or Excel macros.
- Validated and ensured the quality, accuracy, and consistency of data.
- Documented data definitions, business rules, and data lineage.
- Partnered with data engineering teams to design and optimize data pipelines.
- Provided ad-hoc analysis and insights to senior leadership on demand.
- Trained business users on how to interpret dashboards and reports.
- Defined and implemented data governance practices for the project.
- Worked closely with stakeholders to translate business needs into technical data requirements.
- Integrated external data sources (e.g., third-party market data) into internal reporting frameworks.
- Created presentations to summarize analytical findings and recommendations.
- Identified process improvement opportunities through data insights and recommended solutions.
- Supported data migration and data cleansing efforts during system upgrades or new system implementations.
- Ensured compliance with data privacy and security standards (GDPR, CCPA) during data handling and analysis.
SQL Developer
Nationwide
08.2014 - 12.2015
- Experience in developing complex stored procedures, efficient triggers, required functions, creating indexes and indexed views for performance.
- Excellent Experience in monitoring SQL Server Performance tuning in SQL Server.
- Expert in designing ETL data flows using SSIS, creating mappings/workflows to extract data from SQL Server and Data Migration and Transformation from Access/Excel Sheets using SQL Server SSIS.
- Efficient in Dimensional Data Modeling for Data Mart design, identifying Facts and Dimensions, and developing fact tables, and dimension tables using Slowly Changing Dimensions (SCD).
- Experience in Error and Event Handling: Precedence Constraints, Break Points, Check Points, Logging.
- Experienced in Building Cubes and Dimensions with different Architectures and Data Sources for Business Intelligence and writing MDX Scripting.
- Thorough knowledge of Features, Structure, Attributes, Hierarchies, Star and Snowflake Schemas of Data Marts.
- Good working knowledge on Developing SSAS Cubes, Aggregation, KPIs, Measures, Partitioning Cube, Data Mining Models and Deploying and Processing SSAS objects.
- Experience in creating Ad hoc reports and reports with complex formulas and querying the database for Business Intelligence.
- Flexible, enthusiastic, and project-oriented team player with excellent written, verbal communication and leadership skills to develop creative solutions for challenging client needs.
- Expertise in developing Parameterized, Chart, Graph, Linked, Dashboard, Scorecards, Report on SSAS Cube using Drill-down, Drill-through and Cascading reports using SSRS.
Education
Bachelors - Electronics
Osmania University
05.2014
Skills
- Generative AI and LLM orchestration
- Large language models
- Vector databases and retrieval
- Cloud platforms and AI services
- Data engineering and big data
- Data warehousing
- Scripting languages
- Infrastructure and DevOps
- Workflow orchestration
- Data analytics and visualization
- Data science packages
Timeline
Cloud AI Engineer
JPMorgan Chase
02.2024 - Current
Data Engineer
Bank of America
09.2021 - 02.2023
Big Data Engineer
S&P Global Market Intelligence
09.2017 - 08.2021
Data Analyst
HP
01.2016 - 08.2017
SQL Developer
Nationwide
08.2014 - 12.2015
Bachelors - Electronics
Osmania University