Home

Guna Raj Nedunuru - Sr. Gen Ai Developer

[email protected]

Location: San Jose, California, USA

Relocation:

Visa:

Resume file: Guna Raj Nedunur_1782753077323.docx Please check the file(s) for viruses. Files are checked manually and then made available for download.

Guna Raj Nedunuru Sr. Generative AI Engineer [email protected] | +1 7193627749 | Linkedin PROFESSIONAL SUMMARY: Senior Generative AI Engineer with 10 years of experience building enterprise AI and cloud-native platforms focused on Generative AI, LLMs, RAG, NLP, and intelligent search solutions across AWS and Azure ecosystems. Experienced in developing production-grade AI applications that improve knowledge retrieval, automate business workflows, and support scalable enterprise adoption of AI technologies. Expertise in developing and optimizing LLM-powered applications such as conversational AI, enterprise virtual assistants, intelligent document summarization, question-answering systems, and AI-driven search platforms with a focus on contextual relevance, response accuracy, and low-latency inference. Experienced in implementing LLMOps and MLOps best practices, including model versioning, prompt lifecycle management, CI/CD automation, experiment tracking, monitoring, evaluation pipelines, automated retraining, and multi-environment deployment strategies for stable production AI systems. Proficient in Python, SQL, TensorFlow, PyTorch, FastAPI, Flask, MLflow, Docker, and Kubernetes with strong experience building scalable machine learning pipelines, RESTful APIs, microservices, and cloud-native AI applications. Skilled in Responsible AI and enterprise AI governance with experience implementing hallucination mitigation, PII masking, content moderation, RBAC, encryption, secure APIs, and compliance-focused AI deployment standards across enterprise environments. TECHNICAL SKILLS: Programming & Frameworks: Python, SQL, Pandas, NumPy, SciPy, PySpark, TensorFlow, PyTorch, Flask, FastAPI, Matplotlib, Seaborn Generative AI / NLP: Generative AI, LLMs, RAG, Prompt Engineering, Semantic Search, Conversational AI, Vector Search, NLP, Transformer Models, Embeddings, LLMOps, Intelligent Search, AI Governance Machine Learning / AI: Machine Learning, Deep Learning, Neural Networks, Predictive Analytics, Recommendation Systems, Classification, Regression, Forecasting, Supervised & Unsupervised Learning, Feature Engineering, Hyperparameter Optimization, Model Evaluation, Model Monitoring, Automated Retraining, Real-Time & Batch Inference, Time-Series Forecasting, A/B Testing Cloud & AI Services: AWS, Amazon Bedrock, SageMaker, AWS Lambda, Step Functions, S3, ECS, EKS, ECR, IAM, KMS, CloudWatch, OpenSearch, Azure Data Factory, Azure Data Lake, Azure Blob Storage, AKS, Azure DevOps, Azure Monitor, Application Insights, Azure Active Directory, Azure Key Vault, Azure Machine Learning DevOps / MLOps: MLOps, CI/CD, Docker, Kubernetes, MLflow, Model Versioning, Experiment Tracking, Automated Testing, Release Management, Monitoring & Alerting, Autoscaling, Logging, Unit Testing APIs / Data Engineering: REST APIs, Microservices, ETL Pipelines, Data Ingestion, Data Processing, Data Transformation, Feature Stores, Batch Processing, Event-Driven Architecture, Serverless Architecture Security / Governance: RBAC, Secure APIs, Encryption at Rest & In Transit, IAM Policies, Secrets Management, Compliance, Risk Management, Authentication & Authorization Methodologies: Agile, Scrum, Sprint Planning, Backlog Refinement, Architecture Reviews, Release Coordination, Technical Documentation, Operational Runbooks, Cross-Functional Collaboration PROFESSIONAL EXPERIENCE: Comerica Bank, Dallas TX | November 2024 Present Senior Generative AI Engineer Responsibilities: Architected and deployed the enterprise ComerIQ-aligned Generative AI platform supporting document ingestion, embeddings generation, vector indexing, prompt orchestration, and inference pipelines capable of processing 12M+ enterprise documents with low-latency semantic retrieval across distributed banking systems. Developed advanced Retrieval-Augmented Generation (RAG) architectures using Comericas proprietary banking datasets and regulatory knowledge sources to power the banks internal knowledge copilot, improving contextual relevance and factual grounding of LLM-generated outputs for compliance and operations teams. Engineered enterprise prompt engineering workflows for Comericas IT and colleague-facing copilot platform, introducing reusable prompt templates, evaluation pipelines, and feedback-driven tuning that improved response consistency and reduced hallucinations across help desk, document summarization, and policy retrieval use cases. Led enterprise-scale GenAI programs to automate knowledge retrieval, intelligent search, document analysis, and decision-support workflows for Comericas Commercial Banking, Treasury, and Technology divisions, reducing manual research cycles and improving analyst turnaround time. Defined and implemented enterprise LLMOps standards for prompt lifecycle management, model versioning, evaluation pipelines, rollback procedures, release governance, and multi-environment deployment strategies to support Comericas digitally-enabled, data-driven banking vision. Introduced Responsible AI controls including prompt validation, hallucination reduction, PII masking, toxicity filtering, and output moderation to support compliance-focused AI adoption aligned with federal banking regulatory standards. Integrated Generative AI capabilities into internal banking platforms through secure APIs with role-based access controls, enabling governed AI adoption across Commercial Banking, IT, Retail, and Operations departments. Led architecture discussions and mentored engineering teams on GenAI initiatives, standardizing implementation patterns, deployment practices, and AI governance processes aligned with the banks TechVision digital strategy. Delivered NLP and LLM-powered applications including a semantic search platform for internal policy knowledge base, an enterprise virtual assistant for colleague self-service, and document summarization tools for treasury and compliance workflows. Implemented high-performance vector search and embedding-based retrieval using AWS OpenSearch to support low-latency semantic search across large-scale enterprise document repositories. Conducted performance benchmarking, inference optimization, and token consumption analysis to improve throughput, reduce infrastructure costs, and maintain service-level objectives for production AI workloads. Deployed and managed foundation-model workloads using Amazon Bedrock for text generation, conversational AI, embedding generation, and intelligent search use cases. Built scalable data ingestion and embedding generation pipelines using Amazon S3 to manage enterprise datasets, vector indexes, and model artifacts. Leveraged AWS Lambda to automate preprocessing, prompt orchestration, and response post-processing, reducing operational overhead for lightweight Comerica AI inference operations. Orchestrated multi-stage Generative AI workflows using AWS Step Functions to automate ingestion, embeddings generation, retrieval, inference processing, and response delivery pipelines. Containerized and deployed GenAI microservices using Amazon ECS and EKS to support scalable, highly available inference environments for banking AI applications. Implemented operational monitoring and observability using Amazon CloudWatch to track latency, token utilization, and infrastructure health, reducing incident response time by 35% and improving platform stability. Applied AWS IAM security best practices and AWS KMS encryption to protect sensitive banking data within RAG and AI systems, meeting enterprise compliance and governance requirements. Collaborated closely with legal, compliance, privacy, and cybersecurity teams to ensure Generative AI implementations aligned with enterprise governance policies and regulatory standards. Environment: Amazon Bedrock, AWS Lambda, AWS Step Functions, Amazon ECS, Amazon EKS, Amazon S3, AWS OpenSearch, Amazon CloudWatch, AWS IAM, AWS KMS,Python, FastAPI, LangChain, LlamaIndex, RAG, Vector Embeddings, Prompt Engineering, LLMOps, Docker, Kubernetes, CI/CD, MLflow, Git, Responsible AI: PII Masking, Hallucination Mitigation, RBAC, Content Moderation Health First, Rockledge, Florida | March 2023 October 2024 AI/ML Engineer Responsibilities: Built scalable machine learning pipelines for processing structured and unstructured healthcare datasets including Electronic Health Records (EHR), clinical notes, and patient risk data with standardized preprocessing, transformation, and feature engineering workflows. Developed deep learning and neural network models using TensorFlow and PyTorch for clinical NLP, patient readmission risk prediction, appointment no-show forecasting, and intelligent billing classification aligned with Health Firsts population health management initiatives. Implemented predictive analytics models for inpatient health trajectory risk scoring and high-risk outpatient identification, supporting Health Firsts four hospitals including Holmes Regional Medical Centers Level II Trauma Center operational workflows. Led the design and maintenance of model evaluation, monitoring, and automated retraining frameworks to address data drift, maintain model stability, and improve prediction accuracy for clinical decision-support applications across Brevard County health plan operations. Integrated ML workflows with Health Firsts enterprise ETL and EHR data engineering platforms to support reliable, scalable, and low-latency clinical data processing pipelines. Standardized MLOps workflows by introducing CI/CD automation, model versioning, experiment tracking, and automated validation pipelines that improved deployment consistency for Health Firsts clinical AI applications. Implemented serverless preprocessing and inference workflows using AWS Lambda to support low-latency clinical prediction services and event-driven processing for health plan billing and scheduling workflows. Improved model serving efficiency and reduced cloud infrastructure costs through optimized resource allocation, autoscaling strategies, and efficient inference deployment. Deployed, trained, and managed ML models on Amazon SageMaker using managed training jobs, hyperparameter tuning, and scalable inference endpoints for production clinical AI systems. Built and optimized NLP pipelines for clinical text preprocessing, medical entity extraction, tokenization, embedding generation, and transformer-based inference for unstructured EHR data. Fine-tuned pre-trained transformer and foundation models for health-domain-specific applications including medical document summarization, clinical Q&A, and ICD code suggestion to improve contextual relevance across clinical workflows. Configured monitoring, logging, and alerting solutions using Amazon CloudWatch to track model performance, system reliability, and application health across AI platform. Collaborated with clinicians, health plan managers, and IT teams to translate clinical requirements into measurable AI-driven solutions improving patient outcomes and operational efficiency. Orchestrated end-to-end ML workflows using AWS Step Functions for automated training, batch inference, and model update processes supporting supply chain and patient data management transformation. Environment: Amazon SageMaker, AWS Lambda, AWS Step Functions, Amazon ECR, Amazon ECS, Amazon EKS, Amazon S3, Amazon CloudWatch, AWS IAM, AWS KMS, Python, TensorFlow, PyTorch, Scikit-learn, Hugging Face Transformers, NLP, EHR Data Processing, Docker. Onward Technologies, Hyderabad, India | June 2019 November 2022 Machine Learning Engineer Responsibilities: Designed and managed data orchestration workflows using Azure Data Factory while maintaining enterprise datasets in Azure Data Lake Storage Gen2 and Azure Blob Storage for global OEM clients in automotive, industrial equipment, and healthcare sectors. Containerized ML applications using Docker and deployed highly available microservices on Azure Kubernetes Service (AKS) to support scalable production ML workloads for digital engineering services across North American and European manufacturers. Developed and maintained CI/CD pipelines using Azure DevOps to automate model integration, testing, deployment, and release management across Industry 4.0 and Digital Factory engineering projects. Engineered ML-powered predictive maintenance models for industrial equipment and automotive OEM clients, using sensor data and telemetry streams to forecast component failures and optimize maintenance schedules in support of digital manufacturing initiatives. Built scalable end-to-end ML pipelines supporting both batch processing and near real-time inference for OEM clients in transportation & mobility, industrial equipment, and healthcare & Med Tech verticals. Developed RESTful APIs using Flask and FastAPI to expose ML inference services and integrate predictive capabilities into downstream enterprise applications for automotive and industrial OEM clients. Managed ML model deployment and lifecycle operations using Azure Machine Learning, including model registry, experiment management, and managed online endpoints across global delivery centers. Built robust feature engineering and data preprocessing frameworks using Python, Pandas, NumPy, and PySpark to process large-scale manufacturing and engineering datasets across R&D optimization programs. Utilized MLflow for experiment tracking, model lifecycle management, artifact storage, and version control across ML development workflows for digital engineering and data analytics practice. Strengthened platform security by implementing Azure Active Directory authentication, RBAC, and Azure Key Vault for secure credential and secrets management across multi-client cloud environments. Collaborated closely with Data Scientists and OEM domain experts to operationalize research models into scalable, production-grade ML services for automotive ADAS, embedded systems, and healthcare Med Tech applications. Participated in Agile ceremonies including sprint planning, backlog refinement, and peer code reviews as part of TISAX-certified, ISO 9001-compliant engineering delivery processes. Environment: Azure Data Factory, Azure Data Lake Storage Gen2, Azure Blob Storage, Azure Kubernetes Service (AKS), Azure Machine Learning, Azure DevOps, Azure Monitor, Application Insights, Azure Active Directory, Azure Key Vault, Python, PySpark,Docker, Kubernetes. KPIT Technologies, India | January 2015 May 2019 Data Scientist Responsibilities: Performed advanced data preparation, feature engineering, and statistical analysis using Python libraries including Pandas, NumPy, and SciPy to build predictive models supporting KPITs automotive OEM clients in vehicle diagnostics, telematics analytics, and software-defined vehicle development programs. Extracted, transformed, and validated large volumes of structured automotive telemetry and operational data from relational databases using complex SQL queries to support vehicle performance analytics and powertrain reporting initiatives. Performed exploratory data analysis using Matplotlib and Seaborn to identify trends, anomalies, and behavioral patterns in automotive sensor data supporting OEM forecasting, validation, and business decision-making programs. Designed and implemented ML solutions for AI/ML-based Remaining Useful Life (RUL) methodology, supporting predictive maintenance programs for vehicle components across OEM and Tier-1 automotive clients to improve efficiency and reduce maintenance costs. Developed scenario-driven data analysis pipelines to process automotive drive log data and extract critical events for automated driving validation and testing frameworks, supporting V&V coverage for ADAS programs. Built and optimized supervised and unsupervised ML models using Linear Regression, Logistic Regression, Decision Trees, Random Forest, Gradient Boosting, K-Means, and Naive Bayes for automotive operational analytics and vehicle diagnostics classification use cases. Automated recurring reporting and analytical processes using Python-based scripts and scheduled workflows for OEM client engineering teams, improving operational efficiency and reducing manual processing time. Developed time-series forecasting models using ARIMA, moving averages, and trend analysis to support vehicle demand prediction, capacity planning, and component lifecycle forecasting for global automotive production programs. Assessed model effectiveness through cross-validation and evaluation metrics including ROC-AUC, accuracy, precision, recall, F1-score, and confusion matrices for consistent predictive performance across automotive analytics deliverables. Collaborated with automotive engineering teams, OEM analysts, and business stakeholders to translate vehicle software development requirements into scalable analytics and predictive modeling solutions. Performed hypothesis testing and A/B testing to measure model effectiveness, validate recommendations, and quantify business impact for data-driven automotive engineering initiatives. Environment: Python, Pandas, NumPy, SciPy, Matplotlib, Seaborn, Scikit-learn, SQL, Relational Databases, ETL Pipelines, Machine Learning: Random Forest, Gradient Boosting, K-Means, ARIMA, Time-Series Forecasting, Industry Domain: Automotive Software, ADAS Validation, Predictive Maintenance, Vehicle Diagnostics, Software-Defined Vehicles (SDV) EDUCATION: Bachelors in Computer Science National Institute of Technology Warangal, India Keywords: continuous integration continuous deployment artificial intelligence machine learning sthree rlang information technology Texas