AI Platform Engineer

📋 Description

• • Join the Foundation Team at Light, a dynamic group responsible for building the core infrastructure that empowers our entire engineering organization. As a Senior AI Platform Engineer, you will play a pivotal role in architecting and developing the internal "AI Engine" that underpins all AI features across Light's innovative Smart Financial Platform.
• • This is a unique opportunity to move beyond basic API integrations and contribute to the development of a robust Agent Runtime. You will be instrumental in defining internal standards for AI reliability, ensuring that our product teams can confidently and efficiently ship high-quality AI features, significantly reducing development time from weeks to days.
• • Your primary responsibility will be to architect and build a production-grade Agent Runtime. This involves designing and implementing systems for tool registration, managing permissions, defining timeouts, and establishing robust retry semantics for autonomous agents, ensuring their reliable operation.
• • You will also be tasked with evolving our internal GenAI Client and SDKs. The goal is to create a standardized and streamlined "paved road" for product engineers, ensuring that every team at Light interacts with Large Language Models (LLMs) in a consistent, efficient, and best-practice-driven manner.
• • A critical aspect of this role is solving for trust in AI. You will build the "CI/CD for AI," implementing advanced reliability frameworks, establishing golden datasets for benchmarking, and developing comprehensive regression testing pipelines. This will enable the confident deployment of prompts and agents, fostering trust and accelerating adoption.
• • Furthermore, you will lead the integration of Light's AI capabilities with external platforms. This includes leveraging the Model Context Protocol (MCP) and integrating with automation tools such as n8n, expanding the reach and utility of our AI ecosystem.
• • You will design and implement essential governance mechanisms, including rate limits and caching strategies. These measures are crucial for ensuring that our AI infrastructure scales predictably, remains cost-effective, and maintains optimal performance under load.
• • This role demands a systems thinker with a deep understanding of the AI landscape, coupled with practical experience in production engineering. You will be at the forefront of integrating cutting-edge AI advancements into a scalable and reliable financial platform.
• • The ideal candidate will possess a strong systems engineering background, with proven experience in building scalable backend systems or internal developer platforms. A keen focus on latency, observability, and the design of clean, efficient APIs is essential.
• • An "AI Native Mindset" is crucial. You should be passionate about the latest developments in AI, understanding the nuances between different AI concepts like Agents and Chains, and have hands-on experience with protocols like MCP. Staying current with releases from leading AI providers such as OpenAI, Anthropic, and DeepSeek is expected.
• • Proficiency in Kotlin, our core backend language, is highly desirable. However, a strong willingness and demonstrated ability to learn new programming languages quickly will also be considered.
• • A relentless focus on determinism and reliability is paramount. You should understand that software flakiness is a major impediment to AI adoption and possess the expertise to build the necessary evaluations and logging systems to instill confidence in our AI features.
• • Finally, a "Force Multiplier Attitude" is key. You should derive significant satisfaction from empowering other engineers by creating effective tools and platforms, rather than solely focusing on individual feature delivery. This collaborative and enabling mindset is vital for the success of the Foundation Team.