Open to opportunities

Ashritha Velineni

@ashrithavelineni

AI/ML Engineer building production-grade RAG and GenAI systems that automate decisions and accelerate enterprise workflows.

United States

Message

What I'm looking for

I want to build and deploy LLM-powered RAG/GenAI systems end-to-end—connecting scalable data pipelines, MLOps, and microservices—to automate enterprise workflows on AWS/Azure with reliable CI/CD.

I’m an AI/ML Engineer with 4+ years of experience building production-grade ML and GenAI solutions across financial services, cybersecurity, and enterprise SaaS. I focus on turning complex data into reliable, deployable systems.

At T-Mobile, I design and deploy LLM-powered intelligent systems using RAG pipelines, LangChain, and OpenAI APIs for enterprise-scale knowledge retrieval across structured and unstructured data. I’ve built NLP pipelines for intent classification, contextual response generation, and document summarization, improving automation efficiency by ~40% for critical workflows.

I also develop and fine-tune ML models (XGBoost, LightGBM, Random Forest) and deliver end-to-end MLOps with MLflow, Docker, and Kubernetes on AWS SageMaker. On the data side, I implement real-time ingestion and feature engineering using Apache Spark, Kafka, and Airflow to support production load.

Previously at Qualys, I deployed cybersecurity ML and NLP pipelines for threat detection and vulnerability risk scoring, reducing manual triage effort by ~40%. Earlier at Celigo, I built Python-based iPaaS ETL and REST/Webhook integrations for 1,000+ enterprise clients, cutting manual data handling by ~50% and integration error rates by ~30%.

Experience

Work history, roles, and key accomplishments

Current

AI/ML Engineer

Current

T-Mobile

Jan 2025 - Present (1 year 6 months)

Designed and deployed LLM-powered intelligent systems using RAG pipelines and LangChain with OpenAI APIs for enterprise-scale knowledge retrieval. Built NLP and ML pipelines for intent classification, summarization, and classification with end-to-end MLOps on AWS SageMaker and real-time ingestion using Spark, Kafka, and Airflow.

LLM LLMs (LangChain OpenAI API Summarization BERT GPT XGBoost LightGBM Random Forest MLOps MLFlow Docker Kubernetes AWS Sagemaker Apache Spark Kafka Airflow fastAPI AWS EC2 AWS S3 AWS Lambda CI CD

Machine Learning Engineer

Qualys

Nov 2023 - Jul 2024 (8 months)

Developed and deployed ML models for cybersecurity threat detection and vulnerability risk scoring, improving detection precision on large-scale telemetry datasets. Built Hugging Face/BERT-based NLP pipelines for classifying security advisories and auto-tagging CVEs, and implemented monitoring and automated retraining with MLflow and AWS SageMaker.

Python scikit learn XGBoost Hugging Face Transformers BERT NLP Auto Tag CVEs Pyspark SQL MLFlow AWS Sagemaker Model Monitoring REST APIs fastAPI Flask

Python Developer

Celigo

Jan 2022 - Oct 2023 (1 year 9 months)

Developed and maintained Python-based integration workflows and ETL pipelines on the Celigo iPaaS platform to automate data exchange across enterprise SaaS applications. Implemented REST API and webhook integrations for real-time synchronization, including Python-based transformation logic and CI/CD automation with GitHub Actions.