Full Stack Developer – AI & Agentic Systems Intern

About this role

About the role: - Utor Labs, a Bengaluru-based B2B company, is seeking a Full Stack Developer to work on machine-augmented decision tools for organizations - You will build complete web applications spanning frontend interfaces, backend services, and data-driven product features - Your work involves creating and maintaining backend APIs that power these systems - You will take prototypes through to production-ready features, ensuring they perform well, remain secure, and operate reliably at scale - You will integrate large language models into application workflows, using structured outputs and tool calling to enhance user capabilities - You will design and experiment with AI agents that employ tools, coordinate multiple tasks, and execute controlled workflows - You will connect applications to external APIs, databases, and third-party platforms to extend functionality - You will work with data-driven product screens that inform organizational decision-making Tech you'll use: - React for frontend development - JavaScript across the stack - Node.js for backend services - Python for backend logic and AI integration - Django and FastAPI for API frameworks - PostgreSQL for database management - LLMOps for language model operations What we're looking for: - Strong grasp of core programming concepts and architecture principles - Demonstrated ability to learn new tools and frameworks by shipping working code - Experience with every technology listed is not a prerequisite - Comfort building full-stack features from concept to deployment - Understanding of how to structure LLM interactions for reliable outputs - Ability to think about workflow automation and task coordination - Problem-solving mindset when integrating disparate systems - Interest in AI-driven product development Good to know: - Flexible working hours - Women starting or restarting their careers are encouraged to apply Note: Share your resume, GitHub, and a short note about something you built. Highlight one project where an LLM calls a tool or API and explain briefly what broke and how you fixed it.