I teach machines to read, reason, answer — and pick up the phone. At Vivasoft I ship production AI: a voice agent platform that talks over real phone lines, RAG systems over healthcare trial data, document intelligence with OCR, and agents that qualify leads while the sales team sleeps. Built on a data-engineering backbone, designed to survive reality.
Full journey of an AI product: ingestion → embeddings → retrieval → generation → deployment. Retrieval quality beats model size, every time.
Airflow DAGs, BigQuery, Terraform, SQL tuning. Boring infrastructure is why the exciting parts don't fall over.
6 AI products in production across voice, healthcare, HR tech, sales ops, and enterprise support. Trusted in client and sales meetings as the engineering voice. B.Sc. Software Engineering, IUT '22.
Vivasoft's AI voice agent platform. I built the agent's memory — a low-latency RAG stack with Docling parsing, Chonkie chunking, Weaviate, and Azure multilingual embeddings — and the telephony connector bridging PSTN calls from PBX with the agent's WebRTC calls via PJSUA/SIP, so the AI talks on real mobile numbers.
Autonomous agent that evaluates every lead from Vivasoft's social media and website. Webhooks pull leads from Pabbly and WordPress, Gemini rates them against qualification criteria, qualified ones flow into the CRM via API, and the sales team gets pinged on Telegram. Hosted on GCP.
Chat system for Health Technology Assessment trial data. CSV ingestion via Azure Functions into Azure SQL, vectorized into Azure AI Search with LangChain + Azure OpenAI. Dynamic filters by country, drug, and agency with full conversation memory.
Full-stack document intelligence. Gemini-powered OCR extracts key-value pairs, bounding boxes, and confidence scores; humans validate the low-confidence tail. Template management and role-based workflows, containerized on Azure.
RAG assistant for internal support and customer queries. Led ingestion, embedding, and GPT response generation. Real-time analytics for query monitoring and feedback trends, plus a feedback loop that keeps sharpening accuracy.
In-app AI guide for an HR platform — feature help and UI navigation via vector search + GPT-4o mini. Secure isolated backend, and an OpenAI cost-monitoring dashboard so the bill is never a surprise.
Core engineer on Kothon, the AI voice agent platform — agent memory (RAG) and PSTN↔WebRTC telephony. Plus RAG assistants, document intelligence, lead-qualifying agents, and the ETL underneath (Airflow, BigQuery, Terraform). Bridge between engineering and clients in project & sales meetings.
Modernized SQL Server jobs and stored procedures; built data pipelines powering BI and reporting across departments.
Responsive UI design and build — Flutter, Adobe XD, Figma.
Islamic University of Technology, Gazipur, Bangladesh.