I am Sai Surya, a Prompt Engineer with 7 years of experience, evolving from backend Python development to advanced machine learning, NLP, and large language model projects. I design scalable AI solutions—from early-stage data automation tools to enterprise-grade prompt strategies for LLMs like OpenAI GPT-4 and Anthropic Claude. I thrive on turning complex data into practical AI tools that boost business value. I excel in prompt design, fine-tuning, and iterative optimization to deliver contextually accurate, bias-free responses. I work with LangChain, LangSmith, and cloud-native platforms on Azure and AWS, building document intelligence systems, summarization agents, and internal AI assistants. I embrace responsible AI practices, collaborate across functions, and mentor teams to push the boundaries of AI-driven automation.

Sai Surya

I am Sai Surya, a Prompt Engineer with 7 years of experience, evolving from backend Python development to advanced machine learning, NLP, and large language model projects. I design scalable AI solutions—from early-stage data automation tools to enterprise-grade prompt strategies for LLMs like OpenAI GPT-4 and Anthropic Claude. I thrive on turning complex data into practical AI tools that boost business value. I excel in prompt design, fine-tuning, and iterative optimization to deliver contextually accurate, bias-free responses. I work with LangChain, LangSmith, and cloud-native platforms on Azure and AWS, building document intelligence systems, summarization agents, and internal AI assistants. I embrace responsible AI practices, collaborate across functions, and mentor teams to push the boundaries of AI-driven automation.

Available to hire

I am Sai Surya, a Prompt Engineer with 7 years of experience, evolving from backend Python development to advanced machine learning, NLP, and large language model projects. I design scalable AI solutions—from early-stage data automation tools to enterprise-grade prompt strategies for LLMs like OpenAI GPT-4 and Anthropic Claude. I thrive on turning complex data into practical AI tools that boost business value.

I excel in prompt design, fine-tuning, and iterative optimization to deliver contextually accurate, bias-free responses. I work with LangChain, LangSmith, and cloud-native platforms on Azure and AWS, building document intelligence systems, summarization agents, and internal AI assistants. I embrace responsible AI practices, collaborate across functions, and mentor teams to push the boundaries of AI-driven automation.

See more

Experience Level

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

Language

English
Fluent

Work Experience

AI Data Engineer at FASSA
August 1, 2025 - August 1, 2025
Evolved into an AI-focused engineering role, building scalable LLM-based agents, RAG-driven retrieval systems, and multi-agent orchestration pipelines for real-time decision-making in the finance domain. Designed and deployed multi-agent architectures using LangChain, LangGraph, and AutoGen, automating decision workflows and report generation for banking operations. Engineered prompt engineering frameworks for GPT-4 and Claude models, incorporating few-shot learning, prompt tuning, and memory optimization to reduce hallucinations by 30%. Built Retrieval-Augmented Generation (RAG) pipelines with ChromaDB and Pinecone, improving document relevance accuracy. Integrated AI agents into enterprise APIs and banking data systems via FastAPI and Azure Functions, enabling secure LLM interaction with transaction data. Developed and deployed LLM-powered summarization and fraud-detection tools, leveraging OpenAI and Hugging Face transformers for customer insights and anomaly detection. Automated ev
Data/Machine Learning Engineer at Tata Consultancy Service
December 1, 2024 - December 1, 2024
Transitioned from Python development to hands-on machine learning, while beginning to explore natural language processing and LLM APIs in operational AI use cases. Developed LSTM time-series models to detect vibration and temperature anomalies in machinery. Built predictive ML models (XGBoost, LightGBM, scikit-learn) to optimize vehicle maintenance cycles and predict component failures with strong accuracy. Integrated GPT-3 APIs for NLP-based log summarization and fault ticket generation, reducing manual maintenance report creation. Prototyped LLM-based conversational assistant for automotive technicians, enabling natural language diagnostics. Deployed real-time inference pipelines using AWS Kinesis, Flask, and Docker, backed by S3 and CloudWatch for monitoring. Implemented ML lifecycle elements and guardrails (PII masking, jailbreak detectors) with CI/CD processes, enabling reliable retraining and deployment.
Python Developer at Cease Fire
March 1, 2021 - March 1, 2021
Built strong foundations in backend Python development, while initiating early data science experimentation for internal analytics. Developed RESTful APIs using Flask and FastAPI, built ETL pipelines, and automated data ingestion from diverse sources. Created modular job schedulers with cron and Airflow, supporting daily data refreshes. Deployed services on AWS and Azure, containerized with Docker, and monitored using CloudWatch. Initiated ML model experimentation with scikit-learn, and prototyped a recommender system for data-driven personalization. Delivered secure API gateways and IAM policies, and established CI/CD pipelines with GitHub Actions for automated retraining and deployment.

Education

Masters in Computer Science at Easten Illinois University
August 1, 2023 - May 1, 2025

Qualifications

Add your qualifications or awards here.

Industry Experience

Software & Internet, Financial Services, Professional Services