Staff AI Engineer - Search & Discovery

Coupang•Mountain View, CA

About The Position

We are looking for an AI Native, AI First Engineer to pioneer and architect entirely new applications where Generative AI and Large Language Models (LLMs) serve as the fundamental core intelligence. At Coupang, we are redefining the boundaries of what is possible. This role is at the forefront of our invention strategy, building systems that are not just AI-enhanced, but AI-native from the ground up to deliver transformative customer and operational experiences. In this role, you will own the end-to-end lifecycle of high-scale, non-deterministic AI systems—from rapid prototyping and architectural design to full-scale production deployment. You will operate with a full-stack AI mindset, leveraging cutting-edge LLM technology to solve complex problems and create entirely new product paradigms. This is a high-impact, pioneering role where you will drive innovation at scale, shape the future of our product intelligence, and demonstrate a proven track record of taking transformative AI concepts from zero to production.

Requirements

3 years of experience in software engineering, with solid coding skills and critical code review capabilities, as well as a deep specialization in leveraging Large Language Models (LLMs) and Generative AI systems and productivity tools.
Strong product-led engineering mindset with the ability to bridge the gap between cutting-edge AI research and practical, user-centric product features.
Proven experience owning end-to-end AI applications, including: Generative AI agents and conversational interfaces, RAG (Retrieval-Augmented Generation) pipelines, LLM fine-tuning and optimization for specific domains, AI-powered automation and workflow systems.
Demonstrated track record of taking AI-first products from concept to production, driving measurable improvements in user engagement, operational efficiency, or system performance.
Deep technical understanding of modern AI stacks, including: Prompt engineering and LLM orchestration frameworks (e.g., LangChain, LlamaIndex), Vector databases and semantic search architectures, Scalable MLOps for non-deterministic AI models.

Nice To Haves

Experience in high-traffic, large-scale consumer AI environments (e.g., LLM-based assistants, search/recommendation systems, or generative content platforms)
Experience leading or contributing to cross-functional AI research and product engineering teams.
Experience building and launching 0→1 Generative AI products or integrating LLMs into existing complex product surfaces.
Strong background in fast-scaling technology companies with a deep understanding of the challenges in deploying non-deterministic systems at scale.
Passion for continuous experimentation and rapid prototyping to solve ambiguous customer problems using the latest advancements in AI/ML.
Exposure/experience in e-commerce search.

Responsibilities

Design, architect, and own the full lifecycle of novel, end-to-end applications centered on generative AI and LLMs to create new e-commerce experiences.
Develop and manage production AI infrastructure, including vector databases, high-throughput inference, and real-time data pipelines for context enrichment and low-latency serving.
Develop and maintain strong RAG frameworks, grounding AI applications in Coupang’s proprietary product catalog, user history, and operational knowledge bases for factual accuracy and relevance.
Implement advanced prompt engineering, agentic design, and complex LLM chains to build intelligent, stable software services.
Enforce AI reliability, monitoring, and safety to manage model non-determinism, minimizing hallucinations and optimizing large-scale cost-efficiency.
Rapidly prototype and productionize new AI capabilities to drive innovation and advance Coupang's mission to "build the future of commerce."