Staff AI Engineer

About Wati Started as a WhatsApp team inbox in 2020, Wati has evolved into an AI-powered customer engagement platform that goes beyond a single channel. Designed for businesses that sell, support, and grow through conversations, Wati observes customer intent in real time, decides the next best revenue action, and executes it across marketing, sales, and support — on WhatsApp, Instagram, Facebook, TikTok, SMS, and more. Trusted by over 16,000 customers across 190+ countries, Wati simplifies complex operations and business conversations with a unified inbox, no-code automation, and our intelligent AI layer, Astra. Proudly backed by Tiger Global, Sequoia Capital, DST Global, and Shopify, and recognised as a Premium Partner of Meta and Google. About the Role We’re hiring a Staff AI Engineer to own LLM orchestration, RAG, and agent infrastructure at 4B+ messages/year scale. Our platform processes over 4 billion messages per year across 100+ countries. Your mission is to build the robust, scalable, and intelligent systems that turn conversation data into real-time, intelligent customer experiences. In this role, you will lead the architecture, deployment, and optimization of our LLM-driven services — including multi-provider inference orchestration, RAG pipelines, multi-agent workflows, and voice AI. This is a senior IC role with significant technical influence across the AI stack. We need a "builder" who can bridge the gap between complex AI capabilities and massive-scale production environments, ensuring our AI is fast, reliable, and cost-effective. What You Will Own Core LLM Infrastructure: Architect and lead our AI production stack, including multi-provider LLM gateway optimization, token budget management, and low-latency inference routing across OpenAI, Gemini, and other providers. Agentic AI & RAG: Design and implement scalable RAG (Retrieval-Augmented Generation) systems, multi-step AI agent workflows, and tool-calling infrastructure (MCP), ensuring high accuracy and reliability in customer interactions. Voice & Multimodal AI: Lead the evolution of our voice AI layer (WebRTC/realtime) and cross-channel agent coordination across text, voice, and connected messaging platforms. AI Production Lifecycles: Own the "Engineering-to-AI" loop: building automated pipelines for data collection, cleaning, fine-tuning orchestration, and model versioning. Performance & Cost Optimization: Continuously optimize API costs, token budgets, latency, and caching strategies to ensure our 4-billion-message scale remains sustainable and performant. Evaluation & Benchmarking: Build the infrastructure for systematic AI quality assessment, identifying failure modes and ensuring model improvements are grounded in real-world production metrics. Technical Roadmap: Drive technology decisions in close collaboration with engineering leadership, selecting frameworks and architectural patterns that will define our AI future.