OB - Lead AI Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a OB - Lead AI Engineer based in Brazil.

Lead the engineering of a development pipeline where AI agents implement software changes and engineers focus on reviewing and governing outcomes. You’ll own the systems that make agent-driven development reliable, secure, measurable, and safe to scale. This role sits at the intersection of software engineering, CI/CD, platform reliability, security, testing, and AI-assisted development. Rather than maximizing your own output, you’ll optimize the quality and safety of everything the pipeline produces. You’ll work closely with a U.S.-based engineering team and cross-functional partners across SRE, security, legal, and support. The role offers significant autonomy, executive sponsorship, and the opportunity to shape a new engineering operating model.

Accountabilities

• Own the knowledge plane, including project conventions, reusable agent procedures, source indexing, and enforcement mechanisms that ensure AI agents consistently follow established engineering standards.
• Build artifact-based verification gates that validate what actually changed, including test modifications, coverage of new code paths, and protected controls around tests and CI configuration.
• Design secure authority and identity models based on least privilege, short-lived credentials, controlled scope, and clear attribution linking every change to a person, agent, and task.
• Develop and continuously calibrate autonomy tiers that route changes according to reversibility and risk, allowing low-risk changes to proceed automatically while applying stronger controls to high-impact or irreversible changes.
• Engineer containment mechanisms such as circuit breakers, workflow limits, progressive exposure, rollback capabilities, and ceilings for tokens, execution time, retries, and concurrency.
• Own intake and measurement systems, including request routing, deduplication, reproduction context, gate logging, and evaluation harnesses that demonstrate whether configuration changes improve outcomes.
• Establish an evidence-based improvement process using incident records, measurable thresholds, and recurring reviews of the cost and value of individual rules.
• Collaborate with engineering, SRE, security, legal, support, and other teams to establish the policies and operating practices required for safe agentic development.
• Continuously challenge existing controls and remove rules that no longer provide sufficient value, treating simplification and removal as important engineering outcomes.
• Provide technical leadership and establish the standards by which AI-generated software changes are evaluated, governed, and safely deployed.

Requirements

• 10+ years of software engineering experience, including deep hands-on experience building and operating CI/CD pipelines and engineering platforms.
• Strong software engineering fundamentals and the ability to confidently read, evaluate, and govern production-quality code.
• Proven experience owning systems and pipelines that other engineers depend on, including responsibility for reliability and incident resolution.
• Strong security instincts and practical understanding of least privilege, credential management, blast radius, untrusted input, and access-control risks.
• Advanced testing judgment, including experience evaluating test quality, reliability, coverage, and flakiness through measurable evidence rather than assumptions.
• Hands-on experience with agentic coding tools used on real engineering work, with a clear understanding of their strengths, limitations, and failure modes.
• Strong understanding of CI/CD, platform engineering, automation, production reliability, and software delivery workflows.
• Ability to operate effectively across functions and influence stakeholders in areas such as SRE, security, legal, and support.
• Excellent written and spoken English communication skills, with the ability to clearly document conventions, procedures, incidents, policies, and technical decisions.
• Strong analytical judgment, intellectual curiosity, and willingness to continuously challenge assumptions and recalibrate systems based on evidence.
• Comfortable working in an environment where the system is continuously evolving and success depends on preventing failures that have not yet occurred.
• Based in Latin America, with sufficient timezone overlap to collaborate daily with a U.S.-based engineering team.
• This role is particularly suited to an engineer who wants to build and govern the infrastructure around AI-driven software development rather than focus primarily on AI models or prompt engineering.

Benefits

• Full-time, dedicated engagement with genuine ownership of a strategic engineering system.
• Executive sponsorship and protected focus on the AI-driven development operating model.
• Clear scope focused on building safe, measurable automation rather than carrying a separate feature roadmap.
• Opportunity to shape a new approach to software development where AI agents handle implementation and engineers govern outcomes.
• High-leverage work where engineering standards and controls can continuously improve every change passing through the pipeline.
• Curated community of high-caliber, values-driven technology professionals.
• Access to a broader engineering talent network, shared expertise, and knowledge resources.
• Meaningful strategic work with a strong focus on clarity, velocity, outcomes, and sustainable performance.
• Remote opportunity for professionals based in Latin America.