srikarreddyy.com

My Systems

Data Engineering & Cloud Infrastructure:

Designs and implements robust data pipelines and cloud architectures using modern tools like Apache Spark, dbt, Snowflake, and AWS services (Glue, S3, Redshift, Athena). Orchestrates workflows with Airflow and Prefect, deploying scalable solutions via Docker, Kubernetes, and Terraform for high-performance data processing and storage.

Machine Learning Systems:

Develops and deploys machine learning models using TensorFlow, PyTorch, Scikit-learn, XGBoost, and Hugging Face Transformers. Applies advanced techniques in deep learning, reinforcement learning, and ensemble methods for predictive analytics, computer vision, and NLP tasks.

LLM & Generative AI Workflows:

Builds advanced generative AI applications using LangChain, LlamaIndex, CrewAI, and APIs from OpenAI, Anthropic, and Google. Fine-tunes and deploys large language models (e.g., GPT-4o, Claude 3.5, Llama 3.1, Mistral Large) with LoRA/QLoRA, integrating vector databases (Pinecone, Weaviate, Qdrant), modern embeddings (text-embedding-3-large, E5), and advanced prompt engineering for retrieval-augmented generation (RAG), multi-modal AI, and agent-based workflows.

MLOps & CI/CD:

Implements end-to-end MLOps pipelines with tools like MLflow, DVC, Git, and CI/CD platforms (GitHub Actions, Jenkins). Deploys models on cloud platforms (AWS SageMaker, Azure ML, GCP Vertex AI) with monitoring via Prometheus and Grafana, ensuring model reliability, versioning, and automated retraining.

Analytics & Visualization:

Delivers actionable insights through data analysis and visualization using Python (Pandas, NumPy, Plotly), R, SQL, and BI tools (Tableau, Power BI, Streamlit, Looker). Builds interactive dashboards and reports for real-time decision-making and business intelligence.

System Design & Integration:

Architects scalable, integrated systems by connecting APIs, databases, and AI services using microservices architecture, RESTful/GraphQL APIs, and event-driven patterns. Ensures high availability, security, and performance across hybrid cloud environments with tools like Kubernetes, Istio, and cloud-native services.

Why Hire Me?

Results-driven Data and AI Engineer with 3+ years of experience delivering end-to-end solutions across data pipelines, machine learning models, and production AI systems. Proficient in Python, Spark, AWS, and Kubernetes, with expertise in deploying scalable workflows and automating large-scale analytics. Experienced in building intelligent LLM systems using LangChain, LangGraph, and OpenAI. Combines deep technical skills with a focus on business impact to deliver efficient, reliable, and insight-driven solutions. 🚀

My Experience

Experienced in developing scalable data and AI solutions with a strong foundation in software engineering. Skilled in building data pipelines, deploying machine learning models, and leveraging cloud infrastructure and automation to enhance system performance and efficiency.

January 2025 - Present

Machine Learning Engineer

Elastic

I design and deploy end-to-end machine learning pipelines using the Elastic Stack for real-time anomaly detection and log analytics at scale. I fine-tune transformer-based NLP models to improve semantic search and build LLM-powered RAG systems integrated with AWS Bedrock and Elasticsearch vector search. I also implement MLOps pipelines for model versioning, CI/CD, and monitoring, while developing high-throughput data pipelines processing millions of events daily. Additionally, I optimize search and inference performance to reduce latency and enhance system scalability.

May 2021 - May 2023

ML Engineer (Data Scientist)

IBM

I designed and implemented ETL pipelines using Python, SQL, and Apache Spark, improving data processing efficiency and accelerating ML workflows. I built and deployed scalable models on IBM Cloud with real-time inference and automated the ML lifecycle using Airflow to reduce manual effort. I streamlined CI/CD with Docker, Kubernetes, and Jenkins to speed up deployments, and developed both supervised and unsupervised models for use cases like fraud detection and predictive maintenance, improving accuracy while reducing false positives.

March 2024 -May 2025

Course Facilitator

University of Colorado, Boulder

Facilitated three advanced courses in Statistical Methods and Applications, mentoring over 200 students in key areas such as exploratory data analysis, probability theory, statistical modeling, and ethical considerations in data science. Emphasized the development of reproducible statistical workflows and the application of data science techniques to real-world domains like business and climate science. Instruction focused on hypothesis testing, p-value interpretation, and the critical evaluation of statistical methods. Additionally, promoted effective collaboration through self-reflection, peer feedback, and video analysis, while training students to communicate technical results to non-technical audiences and uphold ethical standards in professional practice.

June 2020 - March 2021

Machine Learning Research Assistant

Aurora’s Degree College

As a Machine Learning Research Assistant at Aurora’s Degree College, I developed a deep learning model using a two-stage convolutional neural network (CNN) in PyTorch to classify melanoma tissue images, achieving 85% accuracy across six mutation types. I built an image processing pipeline to handle over 25,000 images and trained models on Google Cloud, improving AUC by 5% through test-time augmentation. I analyzed misclassifications using color-coded tessellations to better understand prediction errors. Based on these findings, I extended the model’s capability to classify human melanoma tissue, enhancing its relevance for real-world medical imaging applications.

My Education

Masters Degree Holder in Data Science at the University of Colorado Boulder (GPA: 3.94), specializing in Machine Learning, Artificial Intelligence and Big data. Previously, I earned a Bachelor of Science with double majors in Mathematics and Statistics & minor in Computer Science from Osmania University (GPA: 3.9), focusing on data structures, algorithms, DBMS , Core Statistics. This academic foundation has strengthened my technical expertise and problem-solving skills for building Data driven solutions.

August 2023 - May 2025

Master in Data Science

University of Colorado Boulder 3.93/4

Machine Learning, Deep Learning,NLP, Statistical Methods & Applications, Data Center Scale Computing

June 2019-July 2022

Bachelor Of Science

Osmania University 3.94/4

Data Structures and Algorithms, DBMS, Linear Algebra, Statistics

My Skills

Specializing in backend development, cloud computing, and automation, I build scalable, high-performance data and AI applications. With a strong foundation in AI, machine learning, deep learning, and MLOps, I deploy end-to-end solutions using tools like AWS, Kubernetes, and modern LLM frameworks.

Python

R programming

SQL

C++

Spark

Airflow

Hadoop

Apache Flink

Tensorflow

Keras

Huggingface

Pytorch

AWS

Power Bi

Tableau

VS Code

MongoDB

Jupyter Notebook

Kubernetes

CI/CD

Git

Docker

Jenkins

Terraform

About Me

I combine expertise in data engineering and machine learning with strong programming and infrastructure skills to deliver end-to-end AI solutions that are efficient, reliable, and impactful.

Name Srikar Reddy Nelavetla

Gender Male

Age 25 Years Old

Maital Status Single

Address Seattle , WA, 98072

Nationality Indian

Experience 3+ Years

Full Time Available

Freelance Available

Phone (+1) 720 234 7493

Email srikarreddyy3@gmail.com

Languages English, Hindi, Telugu

Latest Project

NewYork City Taxi Demand Predictor

Developed an end-to-end pipeline on AWS to process 9.3 million taxi trip records from a three-month period in 2023, integrating weather data to enhance predictive modeling. Trained machine learning models including XGBoost, CatBoost, LightGBM, and AdaBoost, achieving a 15% improvement in accuracy with CatBoost (MAE: 1.5315). Deployed the model using AWS Lambda and API Gateway for real-time predictions. Performance was monitored with AWS CloudWatch, uncovering key demand patterns such as a 20% increase in usage during rush hours and heightened demand in extreme weather conditions, enabling data-driven fleet optimization.

Webscraping, Sklearn, AWS

Live Project Github Repository

AI-Powered Multilingual Detection with Neural-Networks

Developed and optimized neural network architectures, including CNN, BiLSTM, and GRU, for multilingual text classification. Achieved 93.91% accuracy and a 0.94 F1-score using a CNN+BiLSTM hybrid model, while reducing training time by 66%, completing training in just 10 epochs. Additionally, applied Principal Component Analysis (PCA) to compress 768-dimensional XLM-RoBERTa embeddings down to 350 dimensions, preserving 98.6% of the original variance. This dimensionality reduction enabled efficient processing of 1.8 million text samples across 20 different languages.

Tensorflow, Huggingface,Sk Learn

Live Project Github Repository

Cloud-Native YouTube Data Insights

Architected a serverless YouTube trend analysis pipeline using AWS services including S3, Glue, Lambda, Athena, and QuickSight to process over 100,000 daily records and analyze more than 1TB of data for real-time insights. Streamlined ETL workflows by integrating AWS Glue and Lambda, which accelerated data transformation by 70%. Delivered dynamic QuickSight dashboards to visualize trends across 10,000+ videos, enabling actionable insights and efficient data exploration.

Python, Pyspark, AWS

Live Project Github Repository

The LangChain Chronicles

Developed a Retrieval-Augmented Generation (RAG) system using LangChain to extract and answer questions from large-scale datasets, including 2GB of PDFs focused on data science, statistics, and machine learning. Implemented a Conversational Retrieval Chain architecture utilizing FAISS as the vector store, Llama-3 through Ollama for language modeling, and Instruct-XL for embedding generation. Engineered efficient document chunking and preprocessing pipelines using RecursiveCharacterTextSplitter to optimize document retrieval and enhance the accuracy and relevance of query responses.

LangChain, Ollama, Python

Live Project Github Repository

Songs lyric generator using NLP

Developed an NLP-based song lyric generation model by evaluating and comparing Naive Bayes N-Gram, RNN-LSTM, and GPT-2 Transformer architectures. Trained the models on a dataset of 762 songs, achieving 96.16% accuracy with the RNN-LSTM model over 20 epochs, while the Naive Bayes approach produced an average perplexity score of 200. Leveraged GPT-2 with its 1.5 billion parameters to generate coherent and stylistically consistent lyrics with rhyme schemes, showcasing the model’s potential for creative applications in the music industry.

LSTM , Transformers

Live Project Github Repository

PCOS Detection Using Deep Learning

Developed a deep learning-based diagnostic system to detect Polycystic Ovary Syndrome (PCOS) from pelvic ultrasound images using DenseNet121, Vision Transformer, and a custom lightweight CNN (IustNet). Implemented a complete pipeline covering data preprocessing, image augmentation, model training, and evaluation using classification metrics like accuracy, F1-score, and AUC. IustNet demonstrated superior generalization and efficiency, making it ideal for real-time clinical use. Deployed the model through a Gradio web interface and Hugging Face Spaces for accessible browser-based predictions, delivering a reproducible, deployable solution aimed at improving PCOS diagnosis in under-resourced settings.

Deep Learning, GANs , Gradio

Live Project Github Repository

Srikar Reddy Nelavetla

I'm a Data Scientist Data Engineer Machine Learning Engineer AI Engineer

My Systems

Data Engineering & Cloud Infrastructure:

Machine Learning Systems:

LLM & Generative AI Workflows:

MLOps & CI/CD:

Analytics & Visualization:

System Design & Integration:

Why Hire Me?

My Experience

Machine Learning Engineer

ML Engineer (Data Scientist)

Course Facilitator

Machine Learning Research Assistant

My Education

Master in Data Science

Bachelor Of Science

My Skills

About Me

Latest Project

NewYork City Taxi Demand Predictor

AI-Powered Multilingual Detection with Neural-Networks

Cloud-Native YouTube Data Insights

The LangChain Chronicles

Songs lyric generator using NLP

PCOS Detection Using Deep Learning

Let's Connect

Contact Me!

AI Assistant