Full Stack Engineer - AI

About hoichoi

hoichoi is Indias leading Bengali OTT platform — the digital arm of SVF, Eastern Indias leading regional media and entertainment company. We serve 250 million Bengalis worldwide with 650+ films, 185+ originals, and 3,000+ hours of content.

What youll do

This is a role for someone who treats AI tools as infrastructure, not novelty. Youll work across the full stack of what hoichoi builds — integrating LLMs, designing AI-assisted workflows, shipping features, and iterating fast — with the expectation that AI coding tools (Cursor, Claude Code, GitHub Copilot) are running in every session, not opened occasionally.

Youre 2–4 years into your career, which means youve shipped real things, broken real things, and developed genuine instincts about what works. What sets you apart is the speed at which you learn, and the fact that youve already figured out how to make AI do the heavy lifting while you stay accountable for what ships.

• Build and integrate AI-powered features across hoichois internal products — LLM-backed workflows, content generation pipelines, intelligent search, and creative co-piloting tools — using AI coding assistants as your default development environment.
  
• Design and implement prompt architectures for real product features: multi-step chains, retrieval-augmented generation, structured output extraction, and context management across long creative sessions.
• Own your work end-to-end — from design and implementation through testing, deployment, and monitoring. You write the code, you watch it in production, you fix what breaks.
• Evaluate AI output quality systematically: define what good enough looks like for a given creative use case, build lightweight evaluation loops, and iterate until the system behaves reliably — not just impressively in demos.
• Work closely with the cross functional team to understand how teams are using internal tools — and translate that into product improvements that reduce friction and increase creative output.
• Stay ahead of the AI tooling landscape — new models, APIs, frameworks, and approaches land constantly; surface the ones that matter for hoichois use cases and make a clear case for when to adopt them.
• Contribute to shared engineering infrastructure: reusable components, prompt libraries, internal tooling, and documentation that makes the whole team faster.

Qualifications:

Looking to get Placed? Try our Placement Guarantee Plan

Get Hired
• Experience building with LLM — not just calling completions, but designing chains, handling failure modes, and managing output quality.
• Proficiency in and comfort with API integration, async workflows, and lightweight backend services.
• Default user of AI coding tools on real shipped code — with at least one concrete example where AI wrote significant portions that you evaluated, debugged, and took responsibility for.
• Strong debugging instinct: when something breaks — and with LLMs, things break in interesting ways — you diagnose systematically rather than guessing and you document what you find.
• Should know building full stack app in production and know testing.
• Should know how to use AI to improve the building speed not just using AI to make the things done.
• Should know deployment using Docker.

Github or portfolio link