The Role
This is a role for someone who treats AI tools as infrastructure, not novelty. You'll 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.
You're 24 years into your career, which means you've 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 you've already figured out how to make AI do the heavy lifting while you stay accountable for what ships. If you're still getting used to AI tools, this isn't the right moment. If you've already wondered whether you can outpace engineers twice your experience because of how you work, this might be exactly it.
What you'll do
- Build and integrate AI-powered features across hoichoi's 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 LoglineAI's 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
- Experience building with LLM APIs not just calling completions, but designing chains, handling failure modes, and managing output quality.
- Experience with RAG architectures, vector databases, or embedding-based retrieval for knowledge-intensive applications.
- Proficiency in Python 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.
Good-to-Have
- Familiarity with agentic frameworks (LangChain, LlamaIndex, CrewAI, or similar) and an understanding of where they help and where they add unnecessary complexity.
- Exposure to evaluation frameworks for LLM outputs: how to measure quality, reduce hallucination, and build feedback loops that improve a system over time.
Why Join hoichoi
- 250 million Bengalis worldwide a large, loyal, and culturally distinct audience where product decisions have real stakes and generic solutions simply don't work.
- Full ownership of the retention and growth surface. No committee. No six-month approval cycles. If you diagnose it and the case is clear, you ship it.
- We're going AI-native across the entire company in 2026. Growth and retention are among the highest-priority functions for AI embedding this role is at the centre of that effort.
- Direct collaboration with content, marketing, and tech leadership. Your data will be in the room. Your recommendations will be heard.
- A platform where improving retention by even a few percentage points has outsized business impact and where you'll be able to see and own that impact clearly.
Culture & How We Work
At hoichoi, the best idea wins, not the biggest title. We operate in small, cross-functional teams where content, product, growth, and tech sit close together, argue productively, and occasionally steal each other's snacks. It's a lot like a kitchen during a house party: slightly chaotic, everyone's doing three things at once, but somehow the food comes out great.
Ownership here isn't a buzzword; it's the default setting. If something's broken, you don't file a ticket and wait. You're the person who notices the printer is jammed and just fixes it instead of pretending you didn't see it. We ship fast, measure what works, and iterate. Think less perfect deck and more let's see if real viewers actually care.
When big moments arrive, we stretch. But we're equally serious about keeping the pace sustainable, because burnt-out teams build neither great products nor great stories. If that sounds like your kind of chaos, we should talk.
