Staff Engineer (AI Native)

BrazilRemoteFull-timelead

Other

0 views0 saves0 applied

Apply Now

Quick Summary

Overview

This position is listed on behalf of a partner company, which manages all applications and next steps. Our partner is looking for a Staff Engineer (AI Native) based in Brazil.

Technical Tools

Other

We are looking for a senior technical leader to shape how software engineering teams design, build, and operate AI-native systems. In this role, you will establish the standards and practices that enable teams to delegate work to AI agents while maintaining architectural integrity, security, and software quality. You will drive the evolution of AI-assisted development through specification-driven workflows, agent orchestration, automated verification, and shared engineering tools. Working across development, platform reliability, and security, you will help ensure that AI-generated code delivers measurable value for users and the business. You will also mentor engineers, influence technical strategy, and help teams adopt AI responsibly at scale. This is a remote, full-time employee opportunity open to people with disabilities.

Define AI-native engineering standards: Establish verifiable specifications, including preconditions, postconditions, invariants, and Given/When/Then scenarios. Maintain the instructions, context, skills, and constraints that guide AI agents.
Orchestrate AI agents: Break complex engineering challenges into manageable, independently verifiable tasks. Coordinate multiple agents, isolated worktrees, and handoffs between agents and human engineers.
Establish delegation policies: Partner with engineering teams to determine which tasks are suitable for AI delegation and which require human judgment, particularly for product design, strategic decisions, and organizational context.
Strengthen verification practices: Design testing strategies, evaluations, mutation testing, and benchmarks to validate AI-generated code. Guide code reviews toward intent, correctness, and risk rather than code volume alone.
Implement deterministic guardrails: Maintain rigorous CI/CD pipelines, branch protection, CODEOWNERS policies, small delivery batches, and straightforward rollback mechanisms to support safe and reliable releases.
Embed security into agent workflows: Design secure agent identities, least-privilege access, sandboxing, and defense-in-depth controls in collaboration with information security teams.
Develop the shared engineering harness: Continuously improve shared instructions, tools, hooks, and skills, using lessons from failures to strengthen workflows across teams.
Lead production reliability: Define progressive autonomy levels for agents in production, incorporating authorization controls, dry runs, emergency stop mechanisms, service-level objectives (SLOs), observability, and contingency plans.
Apply AI to operational workflows: Use AI where it adds measurable value, including operational playbooks, anomaly detection, root cause analysis, postmortem drafting, and incident handoffs, while preserving effective conventional automation.
Mentor and develop engineers: Coach team members, particularly junior and mid-level engineers, and promote deliberate practice of core software engineering fundamentals to prevent overreliance on AI tools.
Communicate technical strategy: Translate AI capabilities, limitations, risks, and business benefits into actionable insights for technical leadership and business stakeholders, supporting decisions with measurable evidence.

Requirements

~2 min read

Extensive software engineering experience, with a track record as a technical authority in a Staff Engineer, Principal Engineer, or Tech Lead capacity within high-scale production systems.
Strong foundations in software architecture, data structures, invariants, system boundaries, and security principles, with the ability to identify subtle defects in AI-generated code.
Demonstrated, intensive use of AI agents in everyday software development, including expertise in context engineering and specification-driven development.
Practical experience with test-driven development (TDD), automated testing, and evaluation methods, including the design of verification strategies for AI-generated solutions.
Hands-on experience with CI/CD, version control, branch protection, and incremental delivery practices.
Experience operating production systems, including observability, SLOs, incident response, root cause analysis, and postmortems.
Applied security expertise covering least privilege, isolation, identity management, and secrets management.
Strong technical judgment and calibrated skepticism, knowing when to trust AI-assisted workflows, when to verify results, and when human intervention is essential.
Systems thinking and risk assessment skills, with a focus on measurable business outcomes, user impact, and operational reliability.
Excellent communication skills across engineering teams, technical leadership, and business stakeholders, together with a genuine commitment to mentoring.
Nice to have: Experience orchestrating multiple AI agents and maintaining shared engineering harnesses across teams.
Nice to have: Background in Site Reliability Engineering (SRE) or platform engineering, including production agent governance and continuous evaluations such as LLM-as-a-Judge.
Nice to have: Experience with mutation testing, performance benchmarks, or resilience testing.
Nice to have: Publicly shared projects built with AI agents, particularly those demonstrating strong security practices and resistance to attacks.
Nice to have: Experience in payments, fintech, telecommunications, or other high-volume transaction environments.
Nice to have: A proven history of mentoring engineers and developing technical learning programs.