Full-Stack AI Engineer

About the role

This role is a senior Full-Stack AI Engineer position on the platform team focused on building a data ingestion and intelligence layer for enterprise media customers. You will own the complete lifecycle of a system that turns unstructured creative assets and ad performance data into a semantic, vector-based layer. The work sits at the intersection of AI, data engineering, and product, requiring you to move fast while maintaining a high bar for craft and reliability. You will architect durable pipelines, build AI agent tooling, and ship a polished frontend that exposes actionable insights to users. This is a high-impact, high-ownership role where your decisions will directly shape how global brands monitor and optimize large advertising budgets.

Key facts

What you'll do

• Design and build a dual-mode data ingestion engine that handles creative components such as CTAs, headers, body copy, images, video, and metadata, as well as ad performance data tied to those components.
• Implement multi-modal embedding generation and storage that combines vector and structured representations, optimized for retrieval quality and cost.
• Construct AI agent tooling that enables natural language search, comparison, and reasoning across the creative and performance data layer.
• Develop a React frontend that allows users to explore the creative library, query performance data in plain English, and surface actionable optimization insights.
• Create audit-logged decisioning and governance infrastructure to satisfy enterprise-grade requirements.
• Architect durable, idempotent ingestion pipelines at scale, incorporating queues, retries, backpressure handling, deduplication, and schema evolution.
• Generate and manage embeddings for multi-modal creative assets and select and operate the appropriate vector store for the workload.
• Build and maintain retrieval pipelines that deliver accurate, low-latency responses to AI agent tools.
• Ship agent-style systems that include tool use, state management, and multi-step reasoning workflows.
• Develop and maintain the React frontend for the creative intelligence library and the query interface.
• Own the full lifecycle of your systems, from design and build through deployment, monitoring, and iteration.
• Contribute to stack decisions with clear reasoning grounded in production experience.
• Collaborate closely with product and enterprise partners to translate requirements into reliable, scalable systems.

Requirements

• Strong TypeScript skills, using types as a design tool rather than as a formality.
• Production experience with serverless or edge runtimes such as Cloudflare Workers, Vercel, Lambda, or Deno Deploy.
• Demonstrated experience building durable, idempotent ingestion pipelines that include queuing, retry logic, backpressure handling, deduplication, and schema evolution.
• Practical, production-level understanding of embeddings, chunking strategies, and retrieval quality tuning.
• At least one agent-style system shipped to production, covering tool use and stateful multi-step workflows, where framework matters less than the experience gained.
• React fluency with modern patterns and component architecture.
• Comfort operating across two cloud environments and able to reason clearly about when to use edge compute versus managed data and AI services, and how to bridge them effectively.
• Must have prior remote work experience, be fluent with remote collaboration tools and platforms such as Slack, Zoom, Google Workspace, and Linear, and have ideally worked with US or UK-based companies; applications without this experience will not be considered.

Nice to have

• Experience building or operating RAG systems in production.
• Familiarity with current embedding models and the tradeoffs across dimension, quality, and cost.
• Background in ETL design, observability for data pipelines, or evaluation frameworks for retrieval quality.
• Adtech, performance marketing, or marketing analytics background, including understanding of channels, attribution, and creative testing in a live production context.
• Opinions on vector databases such as Cloudflare Vectorize, Vertex AI Vector Search, Turbopuffer, or similar, backed by hands-on experience.

Practical notes

This role is based in South Africa

Cape Town but is listed as Remote with time zone requirements in US Time Zones (EST-PST). The engagement is contract-based. The role requires prior remote work experience with fluency in standard remote collaboration tools.