Experience

Senior Software Engineer at Toosi, building the company's technology end to end: architecture, agent orchestration, web intelligence, backend, full-stack product, evaluation and production deployment on AWS.

• Architecting Toosi, an AI-native outbound platform with agents for prospect discovery, ICP generation, research, outreach, reply intelligence and follow-ups.
• Building multi-agent workflows, LLM orchestration, RAG (Pinecone, Qdrant), tool calling, structured outputs, evaluation and human-in-the-loop systems.
• Spearheaded an AI-powered hotel concierge that lets guests discover destinations, get contextual recommendations, ask questions and request hotel services through conversational AI.
• Built and launched onboarding.krowd.ai, a production AI onboarding assistant that takes restaurant prospects from first interest to self-serve onboarding without waiting for a sales call.

Built and operated production ML and backend platforms used directly by customers, across Kubernetes, API gateways, catalog intelligence, price tracking, CI/CD and full-stack product development.

• Implemented a secure API gateway from scratch with Auth0 and usage logging in NestJS.
• Scaled ML services on Kubernetes to support 1K+ concurrent requests and established GitHub Actions CI/CD for in-house ML services.
• Led development of a web platform for product catalog enrichment and management, across backend services and user-facing workflows.
• Built backend services for real-time price tracking and analysis using NestJS, MongoDB and Elasticsearch.

Joined as the company's first intern and grew into an SDE-1 across recommendation systems, web intelligence, data infrastructure, Kafka, graph databases and cloud automation.

• Built the ingestion pipeline, model generator and the bidding platform.
• Improved a production web crawling service by 7× using Redis, Scrapy and Scrapyd.
• Designed cloud infrastructure-as-code and automated infrastructure management with Ansible.
• Worked across recommendation pipelines, a Neo4j knowledge graph that grew from 20K to 70K nodes, and a three-node Kafka cluster.