Applied AI Engineer at TLDR

TLDR's Applied AI program operates on the core idea that every process at the company should automatically improve as model capabilities advance. An LLM is integrated into every workflow, shifting human roles from manual execution to defining specifications, evaluations, and determining what constitutes high-quality output.

Key Responsibilities:

• Develop and deploy new agents, skills, and platform capabilities across TLDR’s teams.
• Build and implement agents end-to-end, including design, implementation, evaluation, and rollout to internal users.
• Create detailed evals and specs to define measurable quality standards, ensuring workflow improvements are data-driven rather than anecdotal.
• Collaborate with the Applied AI Product Manager to determine what to build, while making independent product decisions for smaller initiatives.
• Work closely with stakeholders in sales, revenue operations, editorial, and people operations to identify optimal LLM integration points within their processes.

Success Metrics:

• Continuous improvement of all company workflows as model capabilities evolve.
• Teams transition from manual execution to writing specs and evals, enabling automated process enhancements without manual intervention.
• Shift toward a push-based workflow, where LLMs handle default tasks and humans are engaged only when necessary.

Qualifications:

• 5+ years of experience, including 2+ years building products and systems with LLMs, with at least one agent you have taken to production and continue to own.
• Proficient in coding with AI tools like Claude Code or Codex.
• Experience writing evals as part of the build process, not retroactively. Ability to articulate how you defined success, measured outcomes, and adjusted based on results.

Cultural Fit:

• Ability to ship end-to-end without waiting for others to define small details.
• Strong product judgment, including the ability to explain what you chose not to build and why.
• Comfortable working in an environment where best practices are still evolving.
• Capable of engaging with non-engineering stakeholders to determine where LLMs can add value.
• Your approach to building has adapted as models have improved, treating capability enhancement as a key design input.
• Desire for broad exposure across nearly every function of a profitable, bootstrapped company with no legacy systems, direct access to the CEO, and an unlimited token budget.