We are looking for a Senior Prompt Engineer to lead the design, testing, improvement, and launch of prompts, AI workflows, and LLM-powered solutions for complex business use cases across multiple countries. You will work closely with product, engineering, data, operations, and regional business teams to turn real business needs into AI capabilities that are reliable, scalable, and measurable.
Success in this role means AI outputs that are more accurate, consistent, and safe; prompt changes that are tested, documented, and traceable before release; shared frameworks that teams in each country can reuse and adapt to local needs; and cross-functional teams that deliver faster because requirements and risks are clearly translated into AI designs.
Process Development: Design lightweight, repeatable workflows and content templates that enable the team to move fast and iterate quickly in a dynamic environment.
Data Analysis: Analyze complex datasets to extract actionable insights and trends. Produce clear, compelling reports that inform partners and stakeholders.
Collaboration: Partner with content and product teams to improve user experience and drive cross-functional initiatives.
...
Full Stack EngineeringFrontend: React, Next.js, TypeScript, modern component architectures, state management, real-time and streaming AI interfaces, agent activity and execution interfaces, data visualization.Backend: Node.js, TypeScript, Python, REST APIs, GraphQL, WebSockets and streaming, event-driven architectures, background workers, job queues, distributed systems, authentication and authorization.
Distributed SystemsDesign systems that reliably execute thousands or millions of AI and data-processing tasks. Kubernetes, Docker, Cloud Run and serverless, message queues, Redis, Kafka or equivalent, distributed job processing, concurrency management, rate limiting, retries, idempotency, fault tolerance, observability. You know how to build systems that stay reliable when agents fail, APIs time out, models hallucinate, or downstream services go away.
Data & Learning InfrastructureBuild the infrastructure agents need to learn from historical executions. PostgreSQL, BigQuery or equivalent data warehouses, ClickHouse or analytical databases, vector databases, embeddings, retrieval systems, event logs, feature stores, analytics pipelines, data ingestion.
...