Staff Engineer, AI R&D

Dlocal LLP; São Paulo; On-site; BRL 400,000 - 560,000; Full time

Job summary

dLocal is seeking a Staff Engineer in AI R&D to set technical direction for agentic and LLM-based systems. You will lead architecture, guide teams, and collaborate with business stakeholders to align priorities and outcomes.

This role emphasizes production-grade reliability, security, and cost discipline in a regulated payments environment. You will mentor engineers, develop playbooks and reusable components, and drive cross-team standards.

Qualifications

• 8+ years of software engineering experience, at senior or Staff level.
• 2+ years hands-on experience building and operating LLM-based systems.
• Experience designing agentic or multi-step AI systems with tool use, orchestration, state or external integrations.
• Strong foundations in distributed systems and in software architecture principles.
• Solid knowledge of cloud infrastructure, preferably AWS, and cost-aware practices.
• Experience with observability, testing and evaluation of complex systems.
• Disciplined engineering practices: code review, CI/CD and controlled deployments.
• Hands-on use of coding agents to design, implement, test and review software.

Responsibilities

• Act as technical lead for AI initiatives from definition to production.
• Translate business goals into technical plans, milestones and trade-offs.
• Define reference architectures and engineering standards adopted by teams.
• Lead design and architecture of AI systems including agentic workflows and state management.
• Establish how AI behavior is measured with metrics and acceptance criteria.
• Drive reliability, scalability and observability for AI services in production.

Skills

Staff-level leadership

LLM-based systems

Distributed systems

Cloud infrastructure

Observability

CI/CD

Code review

Stakeholder communication

Tools

LangChain

LangGraph

Claude Agent SDK

MCP

Kubernetes

Containerized execution

AWS

Job description

AI R&D is dLocal's company-wide AI vertical. We design, build and operate the shared AI platform, agents and automations that let Product, Engineering and business teams create intelligent features and automate work safely. The goal is faster delivery, better operating efficiency and stronger technical differentiation for our merchants and operations.

This is a senior individual-contributor role. It does not require direct people management, but it carries significant technical influence and real ownership: you will be the technical lead for key initiatives, working side by side with your peers and directly with the business. You will work on AI systems that run in production, in a regulated payments environment, where reliability, security and auditability are part of the design from day one.

What's the Opportunity?

As a Staff Engineer in AI R&D, you set the technical direction for agentic and LLM-based systems, raise the engineering bar of the teams around you, and take on the hardest design and production problems. You will join one of our AI R&D teams, matched to your profile and to the company's most pressing needs, and you will work across team boundaries whenever the problem requires it.

You will also take technical leadership of important initiatives: shaping the approach, guiding the team through execution from design to production, and keeping the work aligned with peers across engineering and with the business areas it serves. You will engage with those stakeholders directly, so that decisions are made quickly and with full context.

The areas where you could contribute include:

• AI-native software delivery: agents that support the full software lifecycle, from planning and coding to review, testing and incident response
• Business process automation: a self-service platform where business areas configure and own agentic automations, with human review and full traceability.
• AI platform foundations: shared services such as LLM access and routing, secure tool and system integrations, reusable agent components and governed skills and plugins.

Where you land is decided during the selection process, based on your experience, your interests and the needs of each team.

What Will I Be Doing?

Technical Leadership of Initiatives

• Act as the technical lead of AI initiatives, from the first definition of the problem through delivery in production, working alongside the engineers and team leads who execute them.
• Work directly with peers and business stakeholders to understand needs, agree on scope and priorities, and keep expectations aligned as the work evolves.
• Translate business goals into technical plans, milestones and trade-offs, and raise risks early.
• Make sure initiatives reach production with outcomes that can be measured and explained to the business.

Architecture & Technical Direction

• Lead the design and architecture of AI systems, including agentic workflows, retrieval, tool use, orchestration and state management, built by one or several teams.
• Define reference architectures, patterns and engineering standards that other teams adopt and reuse.
• Define how work is specified for and directed to coding agents (specs, repository context, guardrails and acceptance criteria), so that agent output is reviewable and auditable.
• Make and document trade‑off decisions across quality, latency, cost, security and vendor dependency.
• Solve the most complex technical problems in your area and unblock the teams around you.

Quality & Evaluation of AI Systems

• Establish how AI behavior is measured: evaluation datasets, regression tracking, quality metrics and acceptance criteria for agents and LLM-based features.
• Ensure systems are tested against realistic cases, not only demos, before and after they reach production.
• Define the telemetry needed to understand cost, latency, quality and outcomes end to end.
• Lead operational practices: reliability, scalability, resilience, observability and incident learning for AI services.
• Examine production behavior, identify structural improvements and drive them to completion with the owning teams.
• Keep cost under control through routing, caching, context management and capacity decisions.

Security, Governance & Compliance by Design

• Design controlled access for agents that act on internal systems: permissions, guardrails, audit trails and human-in-the-loop checkpoints.
• Work with Security, Legal, Compliance and IT so that governance requirements are built into reusable components and not rebuilt for every use case.

Multiplying Impact

• Mentor engineers and tech leads, and raise the technical level of the teams you work with.
• Turn what you learn into playbooks, templates, shared libraries and documentation that others can use without you.
• Teach and scale good practices for agent-assisted development across teams: prompting, context management, review workflows and quality gates.
• Communicate clearly with technical and non-technical stakeholders, and align teams around shared standards.
• Share knowledge through internal write-ups and tech talks, and occasionally through external meetups and conferences.

What Skills Do I Need?

• 8+ years of software engineering experience, including significant experience operating at senior or Staff-level scope.
• 2+ years of hands‑on experience building and operating systems based on LLMs, ideally in production.
• Experience designing agentic or multi-step AI systems involving tool use, orchestration, state, retrieval or external integrations.
• Strong foundations in distributed systems, including synchronous and asynchronous communication, and in software architecture principles and practices.
• Solid knowledge of cloud infrastructure, preferably AWS, and of running services securely and cost‑consciously.
• Experience with observability, testing and evaluation of complex systems.
• Experience with disciplined engineering practices: code review, CI/CD, automated testing and controlled deployments.
• Hands‑on, daily use of coding agents to design, implement, test and review software, with sound judgment on when to trust their output and when to challenge it.

Technical leadership

• Track record of technically leading initiatives that involve multiple teams, from design to production.
• Comfortable working directly with business stakeholders and engineering peers to agree on scope, priorities and outcomes.
• Ability to understand trade‑offs, make decisions with incomplete information and stay effective in crisis situations.
• Experience defining engineering standards and best practices that teams actually adopt.
• Able to influence without authority, and to explain technical decisions to non‑specialists in concrete, concise terms.

Nice to have

• Experience with agent frameworks and protocols such as LangChain, LangGraph, the Claude Agent SDK or MCP.
• Experience with Kubernetes and containerized execution environments.
• Experience with LLM gateways, model routing and cost management.
• Background in machine learning or applied research.
• Experience in regulated environments such as payments or financial services.

Mindset

• Builder attitude: you prefer reusable platforms and tools over one-off solutions.
• Curious and biased toward experimentation, combined with disciplined measurement and risk awareness.
• Comfortable with ambiguity in a fast-moving field, and able to structure your own work and keep stakeholders informed.