SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
dLocal is the financial infrastructure powering global commerce in emerging markets, trusted by major companies to process payments and unlock growth across 60+ countries. You will join a team of 1,300+ professionals from 40+ nationalities.
In this Staff Engineer role, you will provide technical leadership across dLocal's AI R&D initiatives, operating at company-wide scope. Your responsibilities span multiple dimensions:
**Technical Leadership & Initiative Ownership**: You will act as the technical lead for AI initiatives from problem definition through production delivery, working alongside engineers and team leads. You'll translate business goals into technical plans and milestones, manage trade-offs, raise risks early, and ensure initiatives reach production with measurable, explainable outcomes.
**Architecture & Technical Direction**: You will lead the design and architecture of AI systems including agentic workflows, retrieval, tool use, orchestration, and state management built by one or several teams. You'll define reference architectures, patterns, and engineering standards that other teams adopt and reuse. You'll make and document trade-off decisions across quality, latency, cost, security, and vendor dependency, and solve the most complex technical problems in your area.
**Quality & Evaluation**: You will establish how AI behavior is measured through evaluation datasets, regression tracking, quality metrics, and acceptance criteria for agents and LLM-based features. You'll ensure systems are tested against realistic cases before and after production, and define telemetry to understand cost, latency, quality, and outcomes end-to-end.
**Production Excellence**: You will lead operational practices for AI services including reliability, scalability, resilience, observability, and incident learning. You'll examine production behavior, identify structural improvements, and drive them to completion. You'll manage cost through routing, caching, context management, and capacity decisions.
**Security & Governance**: You will design controlled access for agents acting on internal systems, including permissions, guardrails, audit trails, and human-in-the-loop checkpoints. You'll work with Security, Legal, Compliance, and IT to build governance requirements into reusable components.
**Multiplying Impact**: You will mentor engineers and tech leads, raise the technical level of teams you work with, and turn learnings into playbooks, templates, shared libraries, and documentation. You'll communicate clearly with technical and non-technical stakeholders and share knowledge through internal write-ups, tech talks, and external venues.
The role offers flexible work arrangements with focus on impact and productivity over fixed hours, combining self-managed focus time with in-person collaboration. You can work from anywhere for up to 3 months annually.
**Requirements**:
- 8+ years of software engineering experience, including significant experience at senior or Staff-level scope
- 2+ years of hands-on experience building and operating LLM-based systems, 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 (synchronous and asynchronous communication) and software architecture principles
- Solid knowledge of cloud infrastructure, preferably AWS, and running services securely and cost-consciously
- Experience with observability, testing, and evaluation of complex systems
- Track record of technically leading multi-team initiatives from design to production
- Comfortable working directly with business stakeholders and engineering peers on scope, priorities, and outcomes
- Ability to understand trade-offs, make decisions with incomplete information, and stay effective in crises
- Experience defining engineering standards and best practices that teams adopt
- Ability to influence without authority and explain technical decisions to non-specialists
**Nice to have**:
- Experience with agent frameworks (LangChain, LangGraph, Claude Agent SDK, MCP)
- Kubernetes and containerized execution environments
- LLM gateways, model routing, and cost management
- Background in machine learning or applied research
- Experience in regulated environments such as payments or financial services
