Home

Tandava Krishna Doddi - Sr AI Ml Data Engineer

[email protected]

Location: Morrisville, North Carolina, USA

Relocation: YES

Visa: H1b

Resume file: Tandava_Krishna_Agentic_AI_Developer_1783444834525.docx Please check the file(s) for viruses. Files are checked manually and then made available for download.

TANDAVA KRISHNA +1 203-589-7608 | [email protected] | linkedin.com/in/tandava-krishna-doddi PROFESSIONAL SUMMARY Agentic AI Developer & Senior AI/ML Engineer with 10+ years of experience designing and deploying Agentic AI systems, multi-agent orchestration frameworks, and LLM-powered enterprise applications. Expertise in Agent-to-Agent (A2A) workflows, Model Context Protocol (MCP) integration, and building autonomous AI solutions that deliver measurable business impact across healthcare, financial services, and retail domains. Expert in Agentic AI development designed and deployed Agent-to-Agent (A2A) orchestration systems and Model Context Protocol (MCP) integrations using LangChain, AutoGen, and CrewAI. Built autonomous multi-agent workflows for document processing, compliance automation, and enterprise system integration, reducing manual review cycles by 40%+. Customer-focused AI strategist collaborates with product managers, architects, and customer teams to identify high-value Agentic AI use cases, assess feasibility, and translate requirements into scalable autonomous solutions. Proven track record integrating AI agents with customer-facing applications and enterprise systems across healthcare, finance, and retail. Rapid prototyper and AI innovator continuously experiments with emerging agentic frameworks, tools, and orchestration patterns (LangGraph, LlamaIndex, Semantic Kernel). Converts cutting-edge AI research into production-ready autonomous systems with clean, well-documented Python and Java code adhering to software engineering best practices. Cloud and systems integration specialist deep expertise in AWS (Bedrock, SageMaker, Lambda), Azure ML, and GCP, with hands-on experience integrating AI agents with APIs, enterprise systems, and customer-facing applications. Ensures performance, scalability, and reliability of agentic AI deployments in production environments. AI research practitioner stays current on autonomous agent research, A2A orchestration patterns, and agentic tooling. Strong communicator who bridges technical complexity and business language for C-suite, customer teams, and cross-functional stakeholders, driving adoption of advanced AI solutions. MLOps and responsible AI practitioner established CI/CD for ML, model versioning, drift detection, explainability (SHAP/LIME), and bias mitigation frameworks. Champions best practices and knowledge sharing across engineering teams to ensure scalable, reliable, and ethical agentic AI systems. CORE COMPETENCIES Agentic AI & LLM Engineering: A2A Orchestration, Model Context Protocol (MCP), Multi-Agent Systems (LangChain, AutoGen, CrewAI, LangGraph), RAG Architectures, Prompt Engineering, GPT-4, Claude, Llama 3.x, LlamaIndex, Semantic Kernel, Vector Databases (Pinecone, Weaviate, FAISS) System Integration & APIs: REST/GraphQL APIs, Enterprise System Integration, Customer-Facing Application Integration, Microservices, Event-Driven Architecture, Kafka, Kinesis, AWS Lambda, Step Functions, Webhooks, OAuth, API Gateway Software Development & Best Practices: Python (Expert), Java, Clean Code, Modular Architecture, Unit Testing, Code Documentation, Design Patterns, Agile/Scrum, Git, CI/CD (Jenkins, GitHub Actions, GitLab CI), Code Reviews, Knowledge Sharing AI/ML Architecture & MLOps: Autonomous Workflow Design, Use Case Identification, Feasibility Assessment, Production ML Deployment, Model Monitoring, Explainable AI (SHAP/LIME), Responsible AI, MLflow, Docker, Kubernetes, Drift Detection, A/B Testing Cloud & MLOps: AWS (SageMaker, Bedrock, Lambda, S3, Glue, Kinesis, Step Functions), Azure ML, CI/CD Pipelines (Jenkins, GitHub Actions), Docker, Terraform, MLflow, Model Versioning, Drift Detection Data Engineering: Apache Spark, Kafka (Streaming & Kafka Streams), Snowflake, AWS Glue, Real-time & Batch ETL/ELT Pipelines, Data Lake Architecture, Feature Engineering, Data Quality Management, Data Lineage, Change Data Capture (CDC) TECHNICAL SKILLS Programming Languages: Python (Expert), SQL (Advanced), Java, Bash/Shell Scripting, C# (Basic) LLM & AI Technologies: Agentic AI (A2A Orchestration, MCP), LLMs (GPT-4, Claude 3.x/4, Llama 3.x, Mistral), Multi-Agent Frameworks (LangChain, LangGraph, AutoGen, CrewAI), LlamaIndex, Semantic Kernel, Prompt Engineering, RAG Pipelines, Vector Databases (Pinecone, Weaviate, FAISS, Chroma), OpenAI API, Anthropic API, AWS Bedrock, Hugging Face Transformers ML/AI Frameworks: TensorFlow, PyTorch, Scikit-learn, XGBoost, LightGBM, Keras, Feature Engineering, Model Training & Evaluation, Hyperparameter Tuning, Explainable AI (SHAP, LIME) Cloud Platforms: AWS (SageMaker, Bedrock, Lambda, S3, Glue, Kinesis, Step Functions, IAM, EC2), Azure (Azure ML, Cognitive Services, Data Factory), GCP (Vertex AI - learning) Data Engineering: Apache Spark (PySpark), Kafka, Snowflake, AWS Glue, Kinesis, Snowpipe, Apache NiFi, Informatica PowerCenter, ETL/ELT Pipelines, Data Lake Architecture, Data Warehouse Design, CDC, Data Lineage Data Governance & Compliance: HIPAA Compliance, PHI Data Handling, Data Quality Management, Master Data Management (MDM), RBAC, Encryption, LDAP, Audit Logging, Regulatory Reporting (CMS, FDA) Databases: Snowflake, PostgreSQL, SQL Server, Oracle, MySQL, MongoDB, Teradata MLOps & DevOps: CI/CD (Jenkins, GitHub Actions, GitLab CI), Docker, Kubernetes (exposure), Terraform, MLflow, Model Versioning, Drift Detection, A/B Testing Monitoring & Observability: ELK Stack, Grafana, Prometheus, CloudWatch, Application Insights, Logging, Alerting, Model Performance Tracking Visualization & BI: Tableau, Power BI, Looker (exposure), Jupyter Notebooks, Streamlit PROFESSIONAL EXPERIENCE Client: Cardinal Health Dublin, OH Dec 2024 Present Role: Agentic AI Developer / Senior AI Engineer Architected end-to-end AI/ML solutions for pharmaceutical distribution and healthcare payer operations, translating complex regulatory requirements into scalable production-grade systems supporting real-time prior authorization, claims validation, and policy compliance workflows. Designed and deployed LLM-powered RAG pipelines for intelligent policy document processing and automated compliance checking, extracting business rules from unstructured payer policies, CMS guidelines, and formulary documents. Reduced manual policy review time by 40% while maintaining 95%+ accuracy in rule extraction. Designed and deployed Agent-to-Agent (A2A) orchestration systems using LangChain, LangGraph, and AWS Bedrock to automate complex enterprise workflows prior authorization validation, compliance checks, and eligibility verification. Implemented Model Context Protocol (MCP) integrations enabling agents to access enterprise data sources, APIs, and tools dynamically with standardized context management. Collaborated with product managers, architects, and customer teams to identify Agentic AI use cases, translate requirements into autonomous workflow designs, and rapidly prototype solutions. Presented business impact analyses to executive leadership, securing buy-in for AI transformation initiatives delivering measurable operational efficiency gains. Engineered custom Python toolsets and REST API wrappers, enabling LangGraph agents to execute multi-step CRUD operations across disparate enterprise systems securely. Optimized agent system performance by refining system prompts, implementing semantic caching, and tuning retrieval parameters, reducing multi-step execution latency by 30%. Scoped and delivered 3+ production agentic workflows in collaboration with cross-functional teams, translating complex business requirements into scalable LangChain architectures. Developed production-ready ML models for entity resolution, medical coding validation, and anomaly detection in claims processing pipelines using Python, TensorFlow, and XGBoost. Deployed models at scale with automated retraining, drift detection, and performance monitoring aligned with CMS quality metrics. Implemented healthcare-specific responsible AI and ethical AI frameworks established bias detection, fairness evaluation (disparate impact analysis), explainability reporting (SHAP/LIME), and audit logging to ensure HIPAA compliance, patient privacy protection, and algorithmic transparency for regulatory scrutiny. Established MLOps best practices including model versioning, CI/CD for ML workflows (Jenkins/GitHub Actions), automated testing, and production monitoring dashboards. Reduced model deployment time from weeks to days while ensuring regulatory audit-readiness. Engineered HIPAA-compliant data pipelines and feature stores on AWS (S3, Glue, Lambda) and Snowflake supporting real-time inference for multiple ML use cases simultaneously. Implemented PHI data encryption, access controls (RBAC), and audit trails meeting healthcare regulatory standards. Designed Snowflake-based data lake architecture integrating AWS services (Glue, Kinesis, Step Functions, Snowpipe) to deliver a unified, governed healthcare data platform. Reduced data ingestion latency by 60% through pipeline optimization and real-time streaming for claims, enrollment, and clinical data. Established comprehensive data quality and validation frameworks with automated profiling and lineage tracking across all data lake layers (raw, curated, ML-ready zones). Ensured data accuracy, completeness, and regulatory compliance for downstream analytics and ML applications. Mentored junior engineers and data scientists on AI architecture patterns, LLM prompt engineering techniques, healthcare domain knowledge (payer operations, prior auth workflows), and production deployment best practices. Environment: Python, Java, Agentic AI (A2A Orchestration, MCP), LangChain, LangGraph, AutoGen, CrewAI, LLMs (GPT-4, Claude/Bedrock, Llama), RAG Architectures, Vector Databases (FAISS, Pinecone), AWS (SageMaker, Bedrock, Lambda, S3, Glue, Kinesis, Step Functions), Snowflake, Apache Kafka, Spark, TensorFlow, Scikit-learn, XGBoost, CI/CD (Jenkins/GitHub Actions), MLflow, Docker, SHAP/LIME, Agile/Scrum Client: USAA San Antonio, TX Dec 2022 Nov 2024 Role: Sr. Data Engineer / ML Engineer Designed and implemented scalable data lake architectures on Hadoop/Cloudera CDP and Kafka-based streaming platforms, ingesting and processing millions of financial transactions daily with sub-second latency SLAs for risk assessment and regulatory reporting. Built high-performance batch and real-time ELT pipelines using Apache Kafka, Kafka Streams, Apache NiFi, and Spark to integrate transactional, clickstream, and event data into unified analytics platform supporting fraud detection, customer analytics, and compliance reporting. Developed and deployed ML models for fraud detection and pattern recognition using Python and statistical techniques, achieving 25% improvement in fraud identification precision over rule-based systems. Built real-time inference pipelines with Kafka Streams for low-latency decision-making. Implemented Change Data Capture (CDC), data lineage tracking, and audit frameworks across critical financial data assets, ensuring data consistency, regulatory compliance, and audit-readiness for risk and compliance reporting (SOX, FFIEC). Established monitoring and observability frameworks using ELK Stack and Grafana to track pipeline performance, data quality, and ML model reliability in production. Implemented automated alerting and incident response workflows. Built comprehensive data quality and validation frameworks ensuring accuracy, consistency, and completeness of datasets used across ML and analytics applications. Enforced data governance policies aligned with financial regulatory standards. Environment: Python, SQL, Machine Learning (Anomaly Detection, Fraud Detection), Kafka Streams, Apache Kafka, Apache NiFi, Hadoop (HDFS, Hive), Cloudera CDP, Jupyter Notebook, ETL/ELT Pipelines, CDC, Data Lake Architecture, ELK Stack, Grafana, CI/CD (Git), PostgreSQL, Oracle, Agile/Scrum Client: Best Buy Minneapolis, MN Apr 2021 Nov 2022 Role: Data Engineer / ML Engineer Translated business requirements into ML-ready data architectures supporting analytics and machine learning use cases across retail systems including customer behavior prediction, inventory optimization, and personalization. Designed and built robust ETL pipelines using Informatica PowerCenter and Apache Spark to ingest, transform, and deliver large-scale structured and semi-structured retail data (POS transactions, inventory feeds, customer behavior streams) into centralized data warehouses. Implemented data profiling, validation, and quality frameworks ensuring accuracy and completeness of data flowing into ML models and reporting systems, reducing downstream data errors by 35%. Optimized SQL-based transformations and data processing logic for high-performance batch pipelines, improving query execution times by up to 50% through indexing, partitioning strategies, and query optimization. Applied statistical analysis and anomaly detection using Python to identify data quality issues and operational trends, improving downstream model accuracy. Environment: Python, SQL, Jupyter Notebook, Informatica PowerCenter, Apache Spark, AWS, CI/CD (Jenkins/Git), Power BI, Tableau, SQL Server, Oracle, Teradata, Agile/Scrum Client: ADP Hyderabad, India May 2017 Dec 2020 Role: Data Engineer Built ETL pipelines and data validation frameworks ensuring data integrity, record consistency, and quality across enterprise data systems supporting financial and operational analytics. Performed time series analysis using Pandas to identify asset variable patterns and project trends, improving project completion forecasting accuracy by 70%. Visualized KPI metrics (resource utilization, profit margins, burn rate) using Tableau to support business decision-making and operational reporting for executive leadership. Environment: SQL, ETL, Tableau, Python, Pandas, Data Validation, KPI Reporting Client: HCL Technologies Hyderabad, India Jun 2014 Apr 2017 Role: Data Analyst Designed and implemented ETL processes using SSIS and Java for data extraction, transformation, and loading into SQL Server data warehouses and data marts. Implemented data validation, cleansing, and quality techniques using SQL Server Data Quality Tools and custom SSIS transformations to ensure data accuracy and reliability. Developed SSRS reports and interactive visualizations in collaboration with business stakeholders, delivering high-quality reporting solutions for operational and strategic decision-making. Environment: SQL, SSIS, SSRS, ETL, SQL Server, Data Warehouse, Data Mart, Java EDUCATION Master's Degree in Computer Science University of Wisconsin, USA (2022) Bachelor's Degree in Electronics and Communication Engineering Vasireddy Venkatadri Institute of Technology, India (2014) Keywords: cprogramm csharp continuous integration continuous deployment artificial intelligence machine learning business intelligence sthree Minnesota Ohio Texas