AI Engineer

ABOUT THE ROLE We are looking for an AI Engineer to help build and scale a company-wide AI platform that will power customer-facing assistants, internal tools and future AI-driven products. This role is not a data science position. You will focus on systems, platforms, reliability and integration, ensuring AI capabilities are safe, scalable, cost-effective and reusable across teams. WHAT YOU’LL WORK ON - Designing and building the core AI platform (gateways, orchestration, retrieval, tooling) - Integrating and operating LLMs via APIs and self-hosted solutions - Creating reusable infrastructure that enables product teams to ship AI features quickly - Implementing safety, compliance and observability for production AI systems - Partnering closely with Product, Backend, Data Science and Security teams to define AI capabilities KEY RESPONSIBILITIES AI PLATFORM & INFRASTRUCTURE - Build and maintain the AI Gateway for routing, rate limiting, experimentation and cost control - Develop the AI Orchestration Layer that manages prompts, retrieval, tool calls and guardrails - Design scalable APIs and SDKs for products to consume AI capabilities KNOWLEDGE & RETRIEVAL SYSTEMS - Implement retrieval-augmented generation (RAG) pipelines using company data - Build document ingestion, indexing and versioning workflows - Ensure AI responses are grounded in approved and up-to-date content MODEL INTEGRATION & MANAGEMENT - Integrate with external LLM providers and manage model configurations - Implement model routing strategies based on cost, latency and use case - Work with prompt templates and system instructions to ensure predictable behavior SAFETY, COMPLIANCE & RELIABILITY - Implement PII handling, content moderation and prompt-injection defenses - Ensure AI systems comply with security and regulatory requirements (fintech context) - Build monitoring, alerting and fallback mechanisms for AI failures OBSERVABILITY & CONTINUOUS IMPROVEMENT - Instrument AI systems with logging, metrics and tracing - Support evaluation workflows and feedback loops to improve quality over time - Help define SLOs and operational standards for AI in production WHAT WE’RE LOOKING FOR REQUIRED EXPERIENCE - 4+ years of experience in backend, platform or infrastructure engineering - Strong experience building production APIs and distributed systems - Experience with cloud platforms (AWS, GCP or Azure) - Solid understanding of system design, scalability and reliability AI & ML LITERACY (NOT DS-HEAVY) - Practical experience integrating AI/ML models via APIs - Understanding of how LLMs work at a systems level (prompts, tokens, latency, cost) - Familiarity with concepts like: - Retrieval-augmented generation (RAG) - Model limitations and hallucinations - AI safety and guardrails - Ability to reason about AI behavior, risks and trade-offs TECHNICAL SKILLS - Strong programming skills in one or more backend languages (e.g., Python, Java, Go, Node.js) - Experience with data stores (SQL, NoSQL, Redis, search engines) - Familiarity with event-driven or async architectures - Experience with observability tools (logs, metrics, tracing) NICE TO HAVE - Experience building internal platforms or developer tooling - Exposure to fintech, payments or regulated environments - Experience with vector databases or search systems - Prior work on chatbots, assistants or workflow automation - Experience designing systems used by multiple teams WHAT SUCCESS LOOKS LIKE - Product teams can ship AI features without rebuilding infrastructure - AI systems are reliable, safe and cost-controlled in production - New AI use cases plug into a shared platform with minimal effort - Leadership has visibility into AI performance, quality and impact WHY JOIN US - Build foundational AI infrastructure used across the company - Work at the intersection of AI, platforms and real business impact - Shape how AI is safely deployed in a fintech/BNPL environment - High ownership, high visibility and long-term technical im