Senior AI Engineer (f/m/d)

# Senior AI Engineer

## Purpose of the Position
We're looking for a Senior AI Engineer to help us build the next generation of AI-native products at Awin. The features you'll work on are used directly by advertisers, publishers and partner managers across our global ecosystem to grow and run their affiliate programs—things like conversational AI experiences, intelligent automation and decision-support tools built on top of Large Language Models and agent-based architectures.

This is a senior product engineering role where you will own real problems end-to-end, make architecture decisions the team builds on and balance technical depth with the realities of shipping software to customers. You are expected to have an opinion on the system design, the evaluation strategy and the way we operate AI in production.

## The Team
You will be joining the AI Solutions team in our Growth Domain. This team is responsible for building AI-native products. Our work is highly visible and every feature you ship can have a real impact on how our customers manage and grow their affiliate programs.

Our engineering culture is built on pragmatic problem solving, strong ownership, fast iteration and a high production bar set through rigorous evaluation, observability and safe-by-default design. We're cloud-first on AWS, working with a Python-based stack that combines agent orchestration, retrieval and standard backend foundations, refreshed as the field moves.

The team practices scrum and you'll have the opportunity to bring new ideas whether that's a different way to solve a problem, an improvement to how we work or sharing best practices for a new technology within the team.

## What You'll Do

• Design, build and operate customer-facing AI features end-to-end, from conversational experiences to intelligent automation
• Architect agent-based systems: multi-step reasoning, tool execution, sub-agent orchestration, state management and streaming, structured outputs, persistent memory and human-in-the-loop approval flows
• Decide how the system grounds, retrieves and constructs context
• Pick the right pattern (retrieval, structured tools, agentic flows) for each problem and be able to defend the choice
• Treat prompt and context engineering as first-class engineering work
• Own AI quality. Build evaluation datasets, regression tests for prompts and agents and the debugging discipline needed to get to root cause across model outputs, retrieval and tool calls
• Make AI production-