I am Aishwarya Ksherasagar, an AI/ML Engineer with 4+ years of experience building production-scale ML and Generative AI systems across the US and India. I specialize in LLM applications, RAG pipelines, and low-latency inference, using tools like LangChain, LlamaIndex, and OpenAI APIs to deliver reliable AI-powered solutions. In my work, I focus on practical ML deployment, model monitoring, and building scalable backend services that enable data-driven decisions. I’m passionate about turning complex data problems into reliable, scalable products and collaborating across teams to drive impact. I’m proficient in MLOps, prompt engineering, fine-tuning (LoRA/PEFT), and evaluating models to reduce hallucinations. I enjoy designing microservice-based architectures, deploying on AWS and Azure, and driving CI/CD, monitoring, and scalable AI solutions that solve real business problems.

Aishwarya Ksherasagar

I am Aishwarya Ksherasagar, an AI/ML Engineer with 4+ years of experience building production-scale ML and Generative AI systems across the US and India. I specialize in LLM applications, RAG pipelines, and low-latency inference, using tools like LangChain, LlamaIndex, and OpenAI APIs to deliver reliable AI-powered solutions. In my work, I focus on practical ML deployment, model monitoring, and building scalable backend services that enable data-driven decisions. I’m passionate about turning complex data problems into reliable, scalable products and collaborating across teams to drive impact. I’m proficient in MLOps, prompt engineering, fine-tuning (LoRA/PEFT), and evaluating models to reduce hallucinations. I enjoy designing microservice-based architectures, deploying on AWS and Azure, and driving CI/CD, monitoring, and scalable AI solutions that solve real business problems.

Available to hire

I am Aishwarya Ksherasagar, an AI/ML Engineer with 4+ years of experience building production-scale ML and Generative AI systems across the US and India. I specialize in LLM applications, RAG pipelines, and low-latency inference, using tools like LangChain, LlamaIndex, and OpenAI APIs to deliver reliable AI-powered solutions. In my work, I focus on practical ML deployment, model monitoring, and building scalable backend services that enable data-driven decisions. I’m passionate about turning complex data problems into reliable, scalable products and collaborating across teams to drive impact.

I’m proficient in MLOps, prompt engineering, fine-tuning (LoRA/PEFT), and evaluating models to reduce hallucinations. I enjoy designing microservice-based architectures, deploying on AWS and Azure, and driving CI/CD, monitoring, and scalable AI solutions that solve real business problems.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert

Work Experience

AI/ML Engineer at Mainstream Technologies
February 1, 2026 - Present
Created and deployed production-grade LLM applications using LangChain and OpenAI APIs, enabling enterprise workflow automation across internal systems. Architected scalable RAG pipelines with optimized chunking and embeddings to improve retrieval accuracy and reduce latency. Engineered end-to-end ML pipelines (ingestion, indexing, retrieval, generation) ensuring reliable, low-latency inference in production. Enhanced response quality through prompt engineering, tuning, and evaluation frameworks to reduce hallucinations. Built scalable backend services with Python, FastAPI, and REST APIs to support high-throughput AI inference. Deployed and monitored AI systems on AWS and Azure, implementing model monitoring, logging, and CI/CD pipelines for robust production performance.
AI/ML Engineer - Intern at Mainstream Technologies
July 1, 2025 - January 31, 2026
Contributed to the development of LLM-powered features using LangChain and OpenAI APIs to support enterprise workflow automation and internal knowledge retrieval. Implemented RAG pipeline components including ingestion, chunking, embedding generation, and semantic retrieval to improve contextual responses. Integrated FAISS and Pinecone for scalable similarity search across large document datasets. Built and tested RESTful APIs with Python and FastAPI to enable low-latency inference and frontend integration. Assisted in prompt engineering, response evaluation, and cloud deployment on AWS/Azure to enhance reliability.
Data Scientist at Accenture
January 1, 2020 - December 31, 2023
Built and deployed machine learning models for classification and regression tasks to support data-driven decision-making. Performed feature engineering, data preprocessing, and model evaluation to improve predictive accuracy and robustness. Enhanced NLP solutions including text classification and sentiment analysis to extract actionable insights from unstructured business data. Designed and maintained scalable data pipelines and ETL workflows to enable efficient data processing and model training. Created dashboards with Power BI and Tableau, enabling stakeholders to monitor KPIs.

Education

Master of Science in Management Science at Arkansas State University, USA
January 1, 2024 - December 1, 2025

Qualifications

Add your qualifications or awards here.

Industry Experience

Software & Internet, Professional Services, Media & Entertainment