AI Engineer - Remote

Immediate joiners only.Compensation: ₹11L to ₹23L per annum, and it grows with every milestone we hit.Xuman.AI is a social app where people post content about what they are open to sharing and experiencing. Someone can discover them by scrolling, and if it resonates and vibes with them, they can connect instantly.On the surface, it collapses fragmented workflows into one system.Underneath, we are building something far deeper: The Human Experience Engine, our Persona Compatibility layer. This engine matches the right person with the right fit at the right time, based on who they are, what they want, and how they connect.The founder's vision is to layer cognitive science into human persona compatibility, leading to hyper-personalized, real-time human connections.Xuman.AI is the productization of the founder's previous bootstrapped venture: ideation, market research, pilots, MVP, and a technical foundation built to scale. The product is built and live on both app stores. We are past the building phase and into distribution: getting it in front of real users and turning it into a repeatable business.Why this role matters:The models move every month, and the products that keep up are built by people who treat agents as the unit of work, not the chat box. This seat builds agentic systems inside a live app with real users and real money: agents that reason, call tools, act, and get checked before anything reaches a person. You ship it, you measure it, and you are the one who knows what the next model release changes.What you'll own:- Agentic systems in production: agents that plan, call tools and act inside a live app, on both stores- The orchestration layer: multi-agent flows, context and memory, routing between models- Guardrails and safety agents: what gets checked before an action or a piece of content reaches a user- Voice and real-time pipelines: speech in, reasoning, speech out, inside a latency budget- Evals and cost: every prompt or model change proven before it ships, every conversation pricedMust have:- Two years or more building with LLMs, and you have shipped something agentic to real users- Agents and tool calling in production, including what happens when a tool fails or a model is slow or wrong- Multi-step or multi-agent orchestration you designed: LangGraph or equivalent, and the judgement to keep it simple- Genuine prompt and system design thinking: you can explain why something works- Evals you built yourself, so a change is proven rather than asserted- Python in production, and comfort in a TypeScript service. Ours is a NestJS gateway.- Structured outputs, streaming and function calling as daily tools, across more than one model provider- Model cost and latency treated as engineering problems, not surprises- You follow the field as it moves: new models, agent protocols, what changed this month and what it means for what you built- You use AI tools (Claude, Copilot, ChatGPT) daily to write, debug, and ship faster. Not optional; this is how we work.What you'll get:- Agentic systems in real hands, with your name on them, on a product that is live today- The frontier as the day job: every new model and protocol is yours to try the week it lands- Real say in how the AI layer is built, from the first feature you ship- The lead seat above you as a real next step, and pay that grows with the milestones- The models and tools you need, with no procurement queueYou are joining before growth, not after. What you own here is real, and it grows as fast as you do.If this seat reads like yours, apply with confidence. Every application is reviewed personally.