How to apply for Automation and Context Engineer

About Iliad

Iliad is a remote-first umbrella organization that advances applied mathematics research in AI alignment through conferences, research incubation, and fellowship programs. Working here means contributing directly to the infrastructure that supports cutting-edge alignment research, rather than just building generic software. It's ideal for someone who wants their engineering skills to have a tangible impact on a small, intellectually rigorous field.

About the role

As an Automation and Context Engineer, you will be the bridge between LLM capabilities and Iliad's research and operations. You'll build custom tools, connectors, and workflows that automate bottlenecks, while also maintaining a living, accurate knowledge base of organizational and research context. This role is uniquely impactful because you'll directly enable researchers and staff to work more effectively with LLMs, ensuring that the context they rely on is trustworthy and up-to-date.

A typical day

Your day might start with a quick sync with researchers to understand a new bottleneck, followed by building a prototype LLM connector to automate a data-gathering task. Later, you might review and update the organizational knowledge base, verifying claims and resolving conflicting information. You could also run a short workshop for staff on effective LLM prompting and output validation, ensuring everyone can leverage your tools safely.

Who Iliad is looking for

• Has hands-on experience building and debugging LLM-powered tools (e.g., using APIs, RAG, agents) and integrating them into real workflows.
• Possesses strong judgment about LLM limitations—knows when to trust outputs and when to verify—and can design validation steps.
• Is meticulous about sourcing, writing, and maintaining decision-relevant context, with a knack for resolving conflicting information.
• Enjoys teaching and enabling others, and can translate technical LLM concepts into practical guidance for researchers and staff.
• Is curious about applied mathematics and AI alignment research, even if not a researcher themselves, and can engage with technical concepts.

Tips for this application

• Highlight specific projects where you built LLM tools or connectors that solved a real bottleneck—include metrics or outcomes.
• Demonstrate your approach to maintaining accurate context: describe a time you resolved conflicting information or updated stale documentation.
• Show familiarity with Iliad's focus areas (applied mathematics, AI alignment) by referencing their conferences, incubation, or fellowship programs in your application.
• Provide examples of how you've helped others use LLMs effectively, such as writing guides, conducting training, or building validation tools.
• Emphasize your ability to work autonomously in a remote setting and to collaborate with researchers who may have varying levels of technical expertise.

What to cover in your cover letter

In your cover letter, focus on: (1) a concrete example of an LLM-powered tool you built that streamlined a workflow, including the problem it solved; (2) your methodology for verifying and updating organizational context, perhaps with a story about resolving a conflict; (3) how you've enabled non-technical colleagues to use LLMs effectively and validate outputs; and (4) why Iliad's mission in AI alignment resonates with you and how you see this role supporting that mission.

Research before applying

• Explore Iliad's website to understand their specific programs (conferences, research incubation, fellowships) and recent activities.
• Read about applied mathematics in AI alignment to familiarize yourself with key concepts and challenges, even at a high level.
• Look up any public talks, papers, or blog posts by Iliad staff to understand their perspectives on LLMs and alignment.
• Investigate the tools and technologies they might already use (e.g., specific LLM APIs, knowledge management systems) to tailor your examples.

Likely interview topics

Based on the job description, expect questions about:

• Walk us through a time you identified an operational bottleneck and built an LLM-powered solution. What was the impact?
• How do you decide when an LLM output is reliable enough to use, and what validation steps do you typically implement?
• Describe your process for maintaining accurate and well-sourced context in a fast-moving organization. How do you handle conflicting information?
• How would you help a researcher who is skeptical about using LLMs in their work?
• What are the limitations of current LLMs that you think are most relevant to building tools for research operations, and how do you work around them?

Common mistakes to avoid

• Focusing only on generic LLM experience without demonstrating how you've applied it to solve operational or research workflow problems.
• Neglecting to show any interest in AI alignment or applied mathematics—this role requires curiosity about the domain.
• Overemphasizing technical skills while ignoring the context-maintenance aspect; this role is as much about judgment and curation as it is about building.