I’m a GenAI Engineer specializing in building production-ready AI solutions with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). I focus on scalable, secure backend systems and real-time data pipelines—turning unstructured and structured information into reliable, high-quality AI experiences. I’ve engineered REST APIs with JWT/OAuth2 security, implemented RAG and document intelligence features using Python, FastAPI, LangChain, and vector databases, and deployed end-to-end ML services using Docker and cloud platforms like AWS/GCP. I enjoy optimizing latency and stability through strong logging/monitoring practices, and I’m passionate about delivering business-focused AI systems in cloud-native environments.

Sri Ramya Siramsetty GenAI Engineer

I’m a GenAI Engineer specializing in building production-ready AI solutions with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). I focus on scalable, secure backend systems and real-time data pipelines—turning unstructured and structured information into reliable, high-quality AI experiences. I’ve engineered REST APIs with JWT/OAuth2 security, implemented RAG and document intelligence features using Python, FastAPI, LangChain, and vector databases, and deployed end-to-end ML services using Docker and cloud platforms like AWS/GCP. I enjoy optimizing latency and stability through strong logging/monitoring practices, and I’m passionate about delivering business-focused AI systems in cloud-native environments.

Available to hire

I’m a GenAI Engineer specializing in building production-ready AI solutions with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). I focus on scalable, secure backend systems and real-time data pipelines—turning unstructured and structured information into reliable, high-quality AI experiences.

I’ve engineered REST APIs with JWT/OAuth2 security, implemented RAG and document intelligence features using Python, FastAPI, LangChain, and vector databases, and deployed end-to-end ML services using Docker and cloud platforms like AWS/GCP. I enjoy optimizing latency and stability through strong logging/monitoring practices, and I’m passionate about delivering business-focused AI systems in cloud-native environments.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Beginner
Beginner
See more

Work Experience

GenAI Engineer
July 1, 2026 - Present
Engineered and deployed Retrieval-Augmented Generation (RAG) systems using Python and FastAPI, improving financial data retrieval efficiency by 40% via scalable real-time access to structured and unstructured data. Developed secure, scalable RESTful APIs using JWT and OAuth2 authentication, supporting high-volume internal applications while maintaining 99.9% system uptime and ensuring secure data access. Orchestrated end-to-end ML model deployment and monitoring using Docker and AWS/GCP, reducing production downtime by 25% and improving deployment reliability. Optimized AI application performance through logging, monitoring, and debugging strategies, reducing response latency by 35% and improving overall system stability and user experience.
GenAI Engineer at JPMorgan Chase
April 1, 2025 - April 1, 2026
Developed RAG-based features using Python, FastAPI, LangChain, and ChromaDB to improve financial document retrieval accuracy by ~30% for internal knowledge searches. Integrated secure RESTful APIs with JWT/OAuth2 authentication to connect LLM-powered services with enterprise applications, ensuring reliable and secure access for internal users. Assisted in deploying and monitoring AI applications using Docker, AWS, and CI/CD pipelines, reducing deployment time by ~25% and improving release consistency. Improved LLM response quality through prompt refinement, embedding optimization, and performance testing, reducing response latency by ~30%.
Software Engineer at CodeNest Solutions
May 1, 2021 - July 1, 2024
Developed scalable backend services and RESTful APIs using Python, Django, and Flask, reducing API response time by ~30% and improving performance for multiple client-facing web applications. Designed and optimized PostgreSQL and MongoDB database queries while integrating third-party APIs, improving data processing efficiency by ~25% and ensuring reliable communication between application components. Built responsive user interface components using JavaScript, HTML, and CSS, enhancing user experience and reducing reported frontend issues by ~20% across multiple client projects. Deployed and maintained applications using Docker, AWS (EC2/S3), Git, and CI/CD pipelines, reducing deployment time by ~25% while improving release consistency and production stability.

Education

Master of Science in Computer Science at Rivier University
September 1, 2024 - June 1, 2026
Bachelor of Technology in Industrial Biotechnology at Bharath Institute of Higher Education and Research
June 1, 2019 - May 1, 2023

Qualifications

Add your qualifications or awards here.

Industry Experience

Financial Services, Software & Internet, Education