Looking for a job

Gyan Gupta

@gyangupta

Message

I build production AI agents, RAG systems, and scalable LLM backend services.

India

Message

What I'm looking for

I'm looking to build production AI systems involving LLM agents, RAG, voice workflows, scalable backend services, and data pipelines.

At Brickfolio, I build AI calling, email, and WhatsApp agents that combine RAG, Gemini APIs, predictive modeling, and real-time customer engagement. I also developed call transcription pipelines processing 10,000+ daily incoming calls.

I've built agentic learning and YouTube analytics platforms with FastAPI, Docker, vector search, Kafka, Hadoop HDFS, and Google Cloud Run. My work spans LLM post-training, model evaluation, fine-tuning, secure MCP servers, and production AI workflows.

Experience

Work history, roles, and key accomplishments

Current

AI Engineer

Current

Brickfolio Pvt. Ltd

Jul 2026 - Present (2 months)

Engineered an end-to-end Pre-Sales AI Calling Agent using Google Speech-to-Speech models with custom RAG, enabling real-time voice queries and automated customer engagement. Designed and deployed an autonomous persona-based Email AI Agent using Gemini APIs and custom memory workflows to handle end-to-end customer communications for executive roles.

Google Speech To Speech RAG Gemini API Memory Workflows predictive modeling LLM WhatsApp Lead Scoring

GenAI Intern

Brickfolio Pvt. Ltd

Apr 2026 - Jul 2026 (3 months)

Built scalable backend microservices using FastAPI, PostgreSQL, and Docker to support asynchronous LLM workloads and high-throughput real-time AI processing. Implemented retrieval-augmented workflows using vector search, embeddings, semantic retrieval, and contextual prompting to improve document search accuracy.

fastAPI PostgreSQL Docker LLM Vector Search Embeddings Semantic Retrieval MCP RBAC Speech to Text Sentiment Analysis

LLM Post Training Intern

Ethara AI

Feb 2026 - May 2026 (3 months)

Contributed to foundation model post-training pipelines involving supervised fine-tuning (SFT), RLHF dataset construction, and rigorous model evaluation. Executed high-density text parsing, chunking, data cleaning, and annotation verification for production-grade evaluation sets.

SFT RLHF Model Evaluation Parsing Data Cleaning Annotations