AI Engineer

We're looking for an AI Engineer to join our engineering team and build the systems that govern how Inventive's AI agents operate in real-world environments. This is a deeply technical role focused on the infrastructure, orchestration, and runtime systems that power our agents. You'll work on execution frameworks, model orchestration, experimentation platforms, and reliability systems that determine how agents'reason, take actions, and continuously improve. You'll collaborate closely with Research, Product, and Infrastructure teams to design and operate AI-native systems that are fast, reliable, and scalable. Success in this role means owning critical systems end-to-end, rapidly iterating based on production feedback, and delivering measurable improvements to agent performance.

Responsibilities:

• Design and build the orchestration systems that power AI agents across our product experiences.
• Develop and evolve agent execution frameworks, harnesses, and runtime infrastructure.
• Build control-plane systems for model routing, planning, tool invocation, and agent coordination.
• Train, test, deploy, and continuously improve AI systems in production environments.
• Optimise AI workflows for latency, reliability, accuracy, and cost efficiency.
• Analyse production failures, identify root causes, and implement systemic improvements.
• Build experimentation platforms, online evaluations, and A/B testing infrastructure to measure agent performance.
• Improve observability, testing, simulation, and monitoring systems to ensure safe and measurable progress.
• Collaborate closely with product and design teams to rapidly prototype, iterate, and deploy new AI-native capabilities.
• Stay current with advances in foundation models and adapt orchestration systems as model capabilities evolve.

Requirements:

• 4+ years of experience building production software systems, backend platforms, AI systems, or distributed infrastructure.
• Fluency in Python and modern ML tooling.
• Strong engineering fundamentals with experience designing and operating reliable systems at scale.
• Experience building and shipping AI-powered products, ML systems, or LLM- based applications.
• Deep understanding of backend systems, APIs, asynchronous architectures, and distributed system tradeoffs.
• Experience owning systems end-to-end, from design and implementation through production operations and iteration.
• Strong debugging and problem-solving skills, with the ability to identify root causes in complex systems.
• Familiarity with cloud infrastructure, containers, databases, and modern deployment workflows.
• Experience using data, experimentation, and evaluation frameworks to drive product and system improvements.
• Ability to move quickly in ambiguous environments and make sound engineering decisions with incomplete information.
• Strong communication skills and the ability to collaborate effectively across engineering, product, and research teams.

Bonus points:

• Experience building agent frameworks, orchestration layers, or autonomous AI systems.
• Experience with multi-agent systems, tool-use frameworks, or model routing architectures.
• Familiarity with evaluation systems, reinforcement learning, or feedback-driven optimisation loops.
• Experience building AI infrastructure at scale, including observability, experimentation, and model serving systems.
• Experience with B2B SaaS products and production AI deployments.
• Contributions to open-source AI, ML, or developer infrastructure projects.