Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I’m a Computer Science Engineering student and AI enthusiast focused on building real-world AI systems using Python, SQL, and modern LLM workflows like RAG, tool/function calling, and agentic multi-agent architectures. I enjoy turning messy data into reliable, evaluated outputs—especially for NLP, text classification, and conversational intelligence. I’ve worked on projects ranging from an AI healthcare multi-agent assistant to a real-time voice conversational assistant, and I’ve contributed to large-scale linguistic data curation and quality assurance for improved model accuracy. I’m motivated to build scalable, production-ready solutions with strong evaluation and clean engineering practices.…I’m a Computer Science Engineering student and AI enthusiast focused on building real-world AI systems using Python, SQL, and modern LLM workflows like RAG, tool/function calling, and agentic multi-agent architectures. I enjoy turning messy data into reliable, evaluated outputs—especially for NLP, text classification, and conversational intelligence. I’ve worked on projects ranging from an AI healthcare multi-agent assistant to a real-time voice conversational assistant, and I’ve contributed to large-scale linguistic data curation and quality assurance for improved model accuracy. I’m motivated to build scalable, production-ready solutions with strong evaluation and clean engineering practices.

Bheeshma Reddy





I’m a Computer Science Engineering student and AI enthusiast focused on building real-world AI systems using Python, SQL, and modern LLM workflows like RAG, tool/function calling, and agentic multi-agent architectures. I enjoy turning messy data into reliable, evaluated outputs—especially for NLP, text classification, and conversational intelligence. I’ve worked on projects ranging from an AI healthcare multi-agent assistant to a real-time voice conversational assistant, and I’ve contributed to large-scale linguistic data curation and quality assurance for improved model accuracy. I’m motivated to build scalable, production-ready solutions with strong evaluation and clean engineering practices.…I’m a Computer Science Engineering student and AI enthusiast focused on building real-world AI systems using Python, SQL, and modern LLM workflows like RAG, tool/function calling, and agentic multi-agent architectures. I enjoy turning messy data into reliable, evaluated outputs—especially for NLP, text classification, and conversational intelligence. I’ve worked on projects ranging from an AI healthcare multi-agent assistant to a real-time voice conversational assistant, and I’ve contributed to large-scale linguistic data curation and quality assurance for improved model accuracy. I’m motivated to build scalable, production-ready solutions with strong evaluation and clean engineering practices.

Available to hire

I’m a Computer Science Engineering student and AI enthusiast focused on building real-world AI systems using Python, SQL, and modern LLM workflows like RAG, tool/function calling, and agentic multi-agent architectures. I enjoy turning messy data into reliable, evaluated outputs—especially for NLP, text classification, and conversational intelligence.

I’ve worked on projects ranging from an AI healthcare multi-agent assistant to a real-time voice conversational assistant, and I’ve contributed to large-scale linguistic data curation and quality assurance for improved model accuracy. I’m motivated to build scalable, production-ready solutions with strong evaluation and clean engineering practices.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Language

English

Advanced

Hindi

Intermediate

Work Experience

Project Developer - Churn Prediction ML System (Deployment)

March 1, 2026 - Present

Developed an end-to-end churn prediction pipeline using 21 behavioral attributes from Telco data. Compared multiple ML algorithms with GridSearchCV and selected Gradient Boosting to achieve ROC-AUC of 0.86. Deployed the trained model with Streamlit for real-time predictions.

Project Developer - MedAssist AI (Multi-agent RAG Healthcare Assistant)

February 1, 2026 - Present

Engineered a multi-agent healthcare assistant for symptom assessment, patient triage, SOAP note generation, and clinical report summarization. Integrated RAG with semantic search, embeddings, and tool calling to generate reliable responses. Designed modular agent workflows with conversational memory to support scalable clinical decision support.

Project Developer - Voice AI Conversational Assistant

January 1, 2026 - Present

Built a real-time conversational voice AI assistant using LiveKit and Deepgram STT with Groq LLM and OpenAI TTS for low-latency speech-to-speech interactions. Implemented a RAG pipeline using ChromaDB with semantic search and conversational memory to answer context-aware queries from a custom knowledge base. Created a modular multi-agent architecture with automated vector DB creation and scalable voice workflows.

Summer Internship Program (DBMS & MySQL training) at Board Infinity

June 1, 2025 - August 31, 2025

Completed DBMS & MySQL training with hands-on projects focused on database design, data management, and database administration. Worked on data modeling, SQL querying (CRUD operations and joins), indexing techniques, and database tuning to ensure data integrity, consistency, and security constraints.

Summer Intern - DBMS & MySQL at Board Infinity – Summer Internship Program

June 1, 2025 - June 1, 2025

Completed DBMS & MySQL training with hands-on projects covering database design, data management, and database administration. Worked on data modeling and SQL querying (CRUD, joins). Implemented indexing techniques and applied database tuning methods to improve data integrity, consistency, and security constraints.

AI Linguist (LLM data curation & evaluation) at Krutrim SI Designs

March 1, 2025 - February 28, 2026

Enhanced LLM performance through large-scale corpus curation, response validation, and linguistic quality assurance. Annotated and refined 5,000+ linguistic data points, contributing to a 10% improvement in model response accuracy. Built and followed annotation/evaluation workflows including prompt evaluation, response ranking, RLHF-style human feedback evaluation, instruction-following checks, dataset validation, and hallucination detection to improve factual accuracy and conversational quality.

AI Linguist at Krutrim SI Designs

March 1, 2025 - February 1, 2026

Enhanced LLM performance through large-scale corpus curation and linguistic quality assurance. Annotated and refined 5,000+ linguistic data points, contributing to ~10% improvement in response accuracy for real-world NLP applications. Supported dataset curation and validation workflows including prompt engineering, response validation, RLHF-style human feedback evaluation, and model benchmarking. Performed prompt evaluation, response ranking, and hallucination detection to improve factual accuracy and instruction-following for conversational AI systems.