AI Agent Engineer

About Us

We are an AI-powered local discovery platform that helps people explore cities and find great places effortlessly. By combining conversational AI, interactive maps, and community-driven content, we enable users to discover restaurants, attractions, and unique local experiences through natural, intuitive interactions. We are building the next generation of AI-powered discovery, reimagining how people explore the world around them.

About the Role

We are looking for an AI Agent Engineer to design, build, and scale production-grade AI Agent systems that power conversational search, personalized recommendations, and end-to-end local discovery experiences. You will own the full lifecycle of Agent architecture, reasoning logic, tool orchestration, and RAG pipelines, turning cutting-edge LLM capabilities into reliable, user-facing systems that directly improve product experience and business metrics.

Responsibilities

• Design and implement production AI Agent / Multi-Agent systems for conversational search, recommendation, and local discovery.
• Build and optimize Agent core modules: planning, memory, tool use, function calling, reflection, and workflow orchestration.
• Develop and scale RAG + multimodal retrieval pipelines across text, image, video, POI, and structured data.
• Integrate, fine-tune, and deploy LLMs and vision-language models for real-time Agent inference.
• Improve query understanding, intent recognition, and response relevance for consumer-facing conversational AI.
• Run A/B tests, analyze performance, and drive measurable improvements in user experience, latency, and quality KPIs.
• Build scalable, low-latency Agent systems that support millions of user interactions.

Requirements

• Bachelor’s degree or above in Computer Science, Artificial Intelligence, or related fields, with solid engineering fundamentals.
• Hands-on experience building and shipping LLM Agent / RAG systems in production.
• Deep understanding of Agent frameworks: LangChain / LlamaIndex / LangGraph or similar.
• Experience with retrieval, embeddings, vector databases, and multimodal models.
• Familiarity with LLM optimization: SFT, LoRA, DPO, inference acceleration is a strong plus.
• Proficiency in Python; experience with Go/C++ is a plus.
• Experience building scalable ML/AI systems in search, recommendation, NLP, or consumer AI products.
• Fast learner, self-driven, and comfortable in a fast-paced startup environment.