Senior AI Engineer

Role: Senior AI Engineer (Contract) Location: Fully Remote (LatAm preferred) About us We are building an intelligent ultra personalized travel companion app powered by advanced AI, designed to make every journey feel more intuitive, personalized, and truly rewarding. We're creating this for people just like us, those for whom travel isn't just a hobby or occasional escape, but a core part of who we are. It's in our DNA, the open road calls, the itch to explore new places runs deep, and the best stories come from real miles logged, unexpected detours, and moments that only happen when you're out there living it. We want teammates who live that lifestyle, who draw from their own adventures to infuse the app with an authentic vibe and intuition that resonates with fellow travelers. If road trips, spontaneous getaways, discovering hidden gems, or turning long drives into meaningful experiences are woven into your life, not just something you read about, you'll bring the empathy, insight, and passion that turns good features into something users feel was built exactly for them. This role is about building for people like you. About the Role We are looking for a Senior AI Engineer who has successfully taken LLM-powered systems out of the playground and into the hands of real users. We don't need prompt engineering in a vacuum - we need someone who has designed, deployed, and sustained production architectures on top of GPT- or Claude-class models, handled live user traffic, and learned the hard lessons around cost, latency, and system failures. You will own our end-to-end LLM architecture, bridging the gap between frontier AI models and our existing application team. What You’ll Do Own the AI Stack: Act as the single owner for our end-to-end LLM infrastructure Architecture Ownership: Design, build, and maintain our core LLM infrastructure, data flows, and orchestration pipelines. Production Operations: Monitor, debug, and optimize real-world model behavior, ensuring high uptime, fast latency, and strict output quality. Cost & Token Optimization: Manage model unit economics-you know how to optimize token usage, leverage caching, routing, or fine-tuning, and can explain where the budget goes. Backend Integration: Collaborate directly with our app development team to expose clean APIs, scale background workers, and integrate LLM features seamlessly into the core product. What We’re Looking For 5+ years of backend engineering experience, including at least 2+ years of hands-on experience building, deploying, and maintaining LLM applications. Proven Track Record: You have shipped at least one LLM-based product to production with active, paying, or high-volume users. You can speak directly to what broke in production and how you fixed it. AI & Language Stack: Expert-level Python skills with deep hands-on experience using frontier models. Backend Fundamentals: Strong grasp of API design, async programming, queueing systems, vector databases, and cloud deployment basics. System Design & Cost Awareness: Practical understanding of model latency tradeoffs, token cost management, context window constraints, and fallback strategies.