LLM Ops Engineer

Job Description

It takes powerful technology to connect our brands and partners with an audience of hundreds of millions of people. Whether you’re looking to write mobile app code, engineer the servers behind our massive ad tech stacks, or develop algorithms to help us process trillions of data points a day, what you do here will have a huge impact on our business—and the world. A Little About Us It takes powerful technology to redefine how hundreds of millions of people interact with the web.

Our team is building the next generation of AI-driven experiences, integrating cutting-edge large language models (LLMs) to provide smarter, faster, and more personal access to information across all major platforms (iOS, Android, MacOS, and Windows). We are the team responsible for the AI systems that power this experience, ensuring they are robust, reliable, and responsible. What you do here will have a huge impact on our business and customers. A Lot About You You are an engineer passionate about the rapidly evolving field of Generative AI and its practical application.

You understand that building an AI product isn’t just about training a model; it’s about the entire lifecycle. You have a keen eye for detail and a rigorous, data-driven approach to LLM evaluation.

You enjoy the challenge of prompt optimization and understand the critical importance of managing data lineage, bias, and model selection. You are a collaborative problem-solver, eager to work in a cross-functional team to maintain and enhance the AI systems that define our browser experience for millions. You thrive in a fast-paced environment and are eager to make an impact.

Responsibilities Design, implement, and maintain robust MLOps/LLM Ops pipelines for continuous integration, delivery, and monitoring of AI models using standard and custom evaluation tools (mainly in GCP) Maintain and enhance evaluation frameworks to benchmark new LLMs (both cloud-based and on-device) for performance, accuracy, and efficiency. Systematically test and refine prompts to optimize for quality, relevance, safety, latency and cost across diverse use cases. Implement and monitor systems for detecting and mitigating accuracy and safety, ensuring our AI features remain safe and reliable over time.

Manage data lineage and versioning for training, validation, and evaluation datasets. Collaborate with engineering teams (iOS, Android, Desktop) to integrate and test AI functionalities, including emerging on-device models.

Troubleshoot and optimize production AI services for latency, cost, and reliability. Perform code reviews, maintain high code quality standards, and ensure proper documentation of systems. Required Qualifications BS in Computer Science or a related field, or equivalent practical experience.

2+ years of professional software development experience. 1+ years of hands-on experience in AI/ML, with specific exposure to Large Language Models (LLMs) and Generative AI. Strong programming proficiency, particularly in Python.

You use AI coding tools as standard (this team is Claude Code for now) Experience with MLOps principles and tools (e. g. , CI/CD pipelines, monitoring, automated testing).

Familiarity with major LLM platforms and APIs (e. g. , VertexAI, OpenAI, AWS Bedrock, or open-source equivalents).

EWJD3