US.

Hi, I am Udyan Upal.

AI-first Software Engineer

I am a Software Engineer with 4+ years of experience building and scaling SaaS platforms end-to-end, from Node.js and TypeScript APIs to PostgreSQL data models and React/Next.js frontends. I specialize in third-party API integrations and production AI features using OpenAI, Claude, RAG, vector databases, background workers, and cloud deployments on AWS and GCP.

Professional Experience

Senior Software Engineer — Factiiv.io

04/2025 – Present | Toronto, Canada (Remote)

  • Architected and shipped a multi-tenant AI agent-builder SaaS platform, owning the full stack from Node.js/TypeScript REST APIs and PostgreSQL schema design through to the React front end; currently serves 1,000+ API requests daily.
  • Built production LLM features on OpenAI and Claude with custom RAG pipelines over Qdrant vector DB (LangChain, LlamaIndex), including chunking, embedding and re-ranking strategies for multi-turn, context-aware responses.
  • Cut hallucinations by ~90% via multi-chain prompting, tool/function calling and optional live web-search retrieval; fine-tuned a GPT model for domain summarisation, improving coherence 15%.
  • Integrated multiple third-party APIs into the platform — LiveKit plus Google Cloud STT/TTS, VAD and turn detection — to deliver real-time bi-directional voice agents with sub-second latency.
  • Built a self-learning LLM feedback loop that captures conversation outcomes and user signals from both the chat and voice interfaces, feeding them back into retrieval ranking, prompt templates and fine-tuning datasets so agent responses measurably improve with usage — lifting resolution quality and customer experience across both channels.
  • Orchestrated asynchronous background workers for model-serving, ingestion and vector-store sync, keeping long-running AI jobs off the request path.
  • Ran code reviews, set backend/AI architecture standards, and mentored junior engineers; continually evaluates emerging frameworks (LangGraph, RAG Fusion, agentic architectures) and brings the useful ones into production.

Backend / Full-Stack Engineer — Luminous Labs

11/2022 – 04/2025 | Dhaka, Bangladesh

  • Designed and built scalable Node.js / Express.js microservices with React + Redux and Next.js clients for a customer-facing SaaS product; improved system scalability 40% and reduced REST API response time 25% through query tuning, caching and Dockerised deployments.
  • Engineered AI/ML features into the platform: RAG pipelines with OpenAI, Weaviate and Redis that lifted retrieval accuracy 35%, plus a visual LLM orchestration tool built with ReactFlow supporting fine-tuning workflows.
  • Owned cloud infrastructure across AWS and GCP — EC2, Route 53 DNS, Cloud Storage and Nginx geo-routing — sustaining 99.9% uptime and 50% faster regional content delivery.
  • Automated build and release with Jenkins CI/CD pipelines, cutting manual deployment effort 70% and doubling release frequency while preserving database integrity and cache consistency.

Skills

AI Coding AgentsClaude Code, Codex, OpenCode, Pi Agent
AI / LLMOpenAI API, Claude API, Function/Tool Calling, RAG, RAG Fusion, LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, Prompt Engineering, Fine-tuning, Embeddings
LanguagesJavaScript (ES6+), TypeScript, Python, SQL
BackendNode.js, Express.js, REST APIs, GraphQL, FastAPI, Microservices, WebSockets, Nginx
FrontendReact, Redux, Next.js, ReactFlow, HTML/CSS, Tailwind
DatabasesPostgreSQL, MySQL, MongoDB, Redis, Qdrant, Weaviate
IntegrationsREST/Webhook APIs, OAuth 2.0, LiveKit, Google STT/TTS
Cloud / DevOpsAWS, GCP, Docker, Kubernetes, Jenkins, CI/CD, Git/GitHub, Grafana, ELK Stack

Contact

Email me