Open to opportunities

Thousifa User

@thousifauser

Message

Full-Stack GenAI/AI/ML engineer building end-to-end RAG and agentic systems with production-grade MLOps.

United States

Message

What I'm looking for

I’m looking to build production-grade GenAI products—RAG/agentic systems, fast and secure user experiences, and solid MLOps. I want teams that value Responsible AI, privacy, and measurable performance improvements (latency, hallucinations, accuracy).

I’m a Full-Stack GenAI/AI/ML Engineer with hands-on experience designing, developing, and deploying machine learning and generative AI solutions. I build RAG and agentic AI applications end-to-end using LangChain and GPT-4 (Azure/AWS), and I focus on secure, responsive user experiences with React/Next.js and FastAPI/Python.

In production work, I own MLOps across AWS and Azure (SageMaker, EKS/AKS, MLflow, CI/CD) and deliver Responsible AI compliance through prompt safety, privacy controls, and detailed usage logging. I’ve reduced answer latency by 35% and minimized hallucinations by 28% through optimized RAG architecture and prompt tuning, and I’ve improved forecast accuracy by 15%.

Experience

Work history, roles, and key accomplishments

Current

Gen AI Engineer

Current

Cognizant

Nov 2025 - Present (7 months)

Developed full-stack GenAI web applications with React and FastAPI, integrating Azure OpenAI for real-time document summarization and conversational Q&A. Built RAG and agentic workflows with LangChain, reducing answer latency by 35% (p95 1.8s→1.2s) and minimizing hallucinations by 28%.

React TypeScript fastAPI Lang Chain RAG Azure OpenAI Azure Cognitive Search Azure Key Vault

LLM Engineer

Citi Bank

Jan 2024 - Nov 2025 (1 year 10 months)

Designed and built LLM applications with GPT-4 (AWS Bedrock) and LangChain for summarization, contextual search, and virtual assistant use cases. Implemented RAG with FAISS/OpenSearch and orchestrated serverless inference pipelines, reducing processing latency by 40%.

LLMs (LangChain RAG OpenSearch Faiss AWS Lambda AWS Step Functions Amazon EKS MLFlow

ML Engineer

Virtusa

Mar 2021 - Dec 2022 (1 year 9 months)

Developed production predictive models using Python, scikit-learn, and XGBoost for forecasting and classification, improving accuracy and reliability. Built end-to-end ML workflows on AWS SageMaker with feature engineering and MLflow-based experiment tracking, deploying via Flask/FastAPI with monitoring for drift and performance.