ML Engineer, Agents & Reasoning

📋 Job Overview

Build agentic AI systems that reason, plan, and act inside real materials discovery workflows. Most agent systems live in clean environments: browsers, codebases, or synthetic benchmarks. At Dunia, agents must reason about messy reality: experiments that fail, data that contradicts itself, and physical systems that don’t reset cleanly. As ML Engineer, Agents & Reasoning, you build the systems that make AI act responsibly inside that reality. You design agents that decide what to do next, use tools intelligently, recover from failure, and know when they don’t know. Your work sits at the boundary between cognition and control.

🏢 About Dunia

Dunia is a company focused on developing AI systems for materials discovery, working at the intersection of machine learning, automation, and scientific research.

🎯 The Role

As ML Engineer, Agents & Reasoning, you will be responsible for building and implementing agentic decision-making systems for materials discovery workflows. You will collaborate with AI researchers, lab teams, and software teams to create systems that can reason about physical systems, operate over experiments and simulations, and translate models into executable actions.

✅ Key Responsibilities

• Design and implement agentic systems that plan, reason, and act across materials discovery workflows
• Develop agents that operate over experiments, simulations, and scientific datasets, selecting next actions under uncertainty
• Define how autonomy is scoped, when humans stay in the loop, and how decisions are escalated
• Implement planning, control logic, and uncertainty-aware decision-making tailored to physical systems
• Encode operational, experimental, and safety constraints directly into agent behavior
• Define stopping criteria, fallback strategies, and recovery mechanisms to prevent brittle behavior
• Collaborate closely with AI researchers to embed predictive models into agent workflows
• Work with lab, automation, and software teams to connect agents to real experimental and simulation systems
• Ensure agent outputs translate into executable actions, not just recommendations
• Build evaluation frameworks that assess decision quality, learning efficiency, and system behavior, not just model accuracy
• Analyze failure cases and iterate on system design based on real-world outcomes
• Help define what “good decisions” mean in scientific discovery contexts
• Translate research concepts into robust, maintainable ML systems
• Instrument agents with logging, monitoring, and diagnostics for observability and debugging
• Take ownership of systems from prototype through deployment and operation

🎁 Benefits

Competitive salary and benefits package.

🛂 Visa & Eligibility

No visa sponsorship or specific eligibility requirements mentioned.