THE ROLE
Engineering & AI Implementation
Work directly with the founder to turn customer needs into working software. This is the more code-focused role: build integrations and agent workflows, investigate problems with the people experiencing them, and follow fixes through to a verified result in the customer’s day-to-day work.
Dialetica builds and operates AI agents that work alongside humans inside companies. We are an early team, with open problems and room to shape both the product and how the company works.
What you will do
- Implement working software. Write and adapt code, integrate APIs and data sources, and build the tools agents need to carry out real responsibilities.
- Own the customer bug loop. Understand reports with the customer, reproduce the issue, inspect logs and agent behavior, implement a fix and confirm with the user that the problem is resolved.
- Build the required workflow. Translate a mapped process into an end-to-end implementation: connect systems, pass the right context, handle exceptions and support human handoffs.
- Test agent behavior. Define acceptance criteria, evaluate tool use and failure recovery, and compare agentic approaches using evidence about quality, latency and cost.
- Improve what we ship. Turn recurring bugs and implementation gaps into product fixes, reusable integrations and clearer operational workflows.
What you bring
- You enjoy spending a substantial part of your time writing code, debugging and understanding how systems work.
- You can work through unfamiliar code, APIs and data, break a problem into testable steps and verify a fix.
- You communicate clearly with customers, ask for the evidence needed to reproduce a problem and stay accountable until the solution works for them.
What we look for
- Practical software problem-solving. Some programming knowledge, or demonstrated ability to use ClaudeCode/Codex/Cursor to build and debug solutions. You should be able to explain what you built, understand its limits and verify that it works.
- Scientific curiosity about agentic systems. An interest in planning, tool use, memory, evaluation and multi-agent coordination. Read, form hypotheses, run experiments and update your views when the evidence changes.
- Clear communication and ownership. Listen carefully, ask useful questions, make trade-offs explicit and follow work through to a verified outcome.
- Evidence of learning and execution. A project, integration, analysis, automation or problem you solved. Work, study and personal projects all count.
You do not need to know everything already. We value the ability to learn, build and distinguish what has been tested from what is still a hypothesis. Building and talking to customers are part of this role.
SHOW US YOUR WORK
How you think.
What you have built.
Tell us about your experience, something you built or a problem you solved, and a question about AI agents you would like to investigate. A repository, demo or clear account of your work is a good place to start.