Sri Hari Mamillapalli

Data enthusiast with 7+ years of broad-based experience in building data-intensive applications, overcoming complex architectural, and scalability issues in diverse industries. Proficient in predictive modeling, data processing, and data mining algorithms, as well as scripting languages, including Python and R. Capable of creating, developing, testing, and deploying highly adaptive diverse services to translate business and functional qualifications into substantial deliverables with MLops and cloud technologies.

• Developed and deployed anomaly prediction version to locate anomalies for Mercedes-Benz Client Which decreased the time taken to remedy a problem from 1-2 hour to 15 minutes.
• Successfully integrated recommendation engine with ServiceNow booking engine to reduce L1 ticket processing time from 10 minutes to 6 minutes and was named top collaborator of the team.
• Created a risk forecasting system for Cisco client that increased customer retention by 6%.
• Promoted from Senior Engineer to Lead Engineer, in less than 12-months.
• Improved delivery of AIOps Product by bringing down cost, realizing overall increase in customer satisfaction and cost efficiency.

AIOps (Anomaly Detection)
Problem Description: The organization faces challenges in monitoring a large number of dashboards, resulting in a significant amount of time being consumed in identifying and addressing problems. This extended time to identify issues has led to prolonged service level agreement (SLA) timelines for issue resolution.
* Implemented real-time data aggregation for over 250 microservices from Datadog and SQL servers.
* Researched and built ML models to predict anomalies from time series data and determine influential features.
* Deployed trained models into production pipelines using Databricks, Azure DevOps (ADO), and Azure Data Factory on Azure.
MREBot (AI ChatBot)
Problem Description: The organization encountered difficulties in managing a high volume of key performance indicators (KPIs) on the dashboard. This posed challenges in effectively monitoring and understanding the metrics due to the overwhelming number of KPIs displayed. Additionally, there were knowledge gaps among team members, further exacerbated by limited availability of engineers around the clock.
* Integrated large chunks of data from Delta Lake and Confluence into an openAI large language model with Langchain.
* Built a complex pipeline utilizing multiple Azure services such as Databricks, Azure Synapse Analytics, Azure OpenAI, and Azure Search.
*Created a unified platform for handling queries related to organizational data.
MCC (Action Recommendation Engine)
Problem Description: Service engineers faced a significant time-consuming task of identifying the source resource when troubleshooting incidents, resulting in delays in incident resolution and impacting the service level agreement (SLA). There was a need to streamline the process and reduce the time spent on identifying the source resource, thus improving the overall SLA for incident resolution.
* Aggregated historical data from various sources into S3 buckets on AWS as Parquet files.
* Developed a recommendation engine using NLTK framework and random forest to suggest the next course of action for support engineers, thus reducing ticket resolution time.
DNAc (Risk Prediction Modeling)
Problem Description: The organization experienced a rise in customer churn rate and a decline in platform resource uptime, primarily driven by customer dissatisfaction. This posed a significant challenge in retaining customers and maintaining a high level of service reliability. There was a need to address these issues by identifying the root causes of customer dissatisfaction and implementing measures to improve customer retention and increase platform uptime.
* Collected data related to switches, APs, and routers from AWS S3 buckets using PySpark and converted it from unstructured to structured data.
* Developed a logistic regression model for predicting devices at risk, aiding in proactive risk management.
Ex-Dat Automation (ML Platform)
Problem Description: The organization faced challenges in utilizing machine learning (ML) algorithms and conducting data analysis on the platform due to its inherent complexity. Users found it difficult to navigate through the intricacies of ML algorithms and perform effective data analysis. There was a need to simplify the process, making it more accessible and user-friendly, enabling users to leverage ML algorithms and conduct data analysis with ease and efficiency.
* Implemented various supervised and unsupervised ML algorithms for the platform backend using Python and R languages.
* Ex-Dat is a machine learning software platform owned by Infosys, utilized for predictive analytics and data analysis.

• AWS Solutions Architect Associate
• Microsoft Certified: Azure Fundamentals
• Google Analytics Certification

Leadership: Successfully led cross-functional teams, making strategic decisions and driving project success.
Communication: Excellent verbal and written communication skills, adept at conveying complex ideas and instructions.
Problem-solving: Proven ability to analyze and resolve complex problems, implementing effective strategies.
Decision-making: Skilled in making informed and timely decisions, considering multiple factors and team impact.
Teamwork: Strong collaboration skills, fostering cooperation and achieving shared goals.
Adaptability: Quick to adapt to changing circumstances, embracing new technologies and navigating dynamic work environments.
Time Management: Exceptional ability to prioritize tasks, meet deadlines, and manage workload efficiently.
Strategic Thinking: Demonstrated strategic thinking abilities, aligning goals with organizational objectives.
Mentoring and Coaching: Experience in guiding and developing team members, providing constructive feedback for growth.