Senior Software Engineer – AI Infrastructure

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior Software Engineer – AI Infrastructure based in Brazil. We are seeking an experienced software engineer to build and operate the production infrastructure that powers intelligent AI agents at scale. In this role, you will design high-performance services that support model inference, orchestration, and execution across complex distributed systems. You will help transform experimental AI capabilities into reliable, scalable production solutions serving millions of users. Working primarily with Rust, you will address critical challenges in latency, throughput, fault tolerance, observability, and infrastructure efficiency. You will collaborate closely with AI engineering, agent systems, and infrastructure teams to establish robust operational standards and ensure safe, predictable system behavior. This remote opportunity offers the chance to shape foundational AI infrastructure in a demanding, high-impact financial technology environment.

AI Infrastructure Development and Architecture Design, develop, and maintain the infrastructure layer that powers AI agent systems in production environments. Build high-performance backend services using Rust to support model inference, agent orchestration, and execution workflows. Architect scalable distributed systems capable of handling high request volumes and supporting millions of users. Establish foundational infrastructure components and reusable system primitives that enable AI agents to interact reliably with internal services. Contribute to critical architecture decisions, balancing performance, reliability, scalability, and operational cost. Machine Learning Infrastructure and MLOps Develop and maintain reliable infrastructure for model serving, deployment, evaluation, and production monitoring. Implement operational patterns that support consistent model delivery, performance evaluation, and continuous improvement. Collaborate with AI and applied engineering teams to move experimental prototypes into robust, production-ready systems. Optimize model inference and orchestration workflows to improve latency, throughput, resource utilization, and cost efficiency. Support the integration of AI capabilities into production systems while maintaining predictable and reliable execution. Reliability, Observability, and Performance Design and implement monitoring, logging, tracing, and observability mechanisms to provide visibility into system behavior. Establish guardrails, fault-handling strategies, and recovery mechanisms for agent-driven workflows and distributed services. Identify and resolve performance bottlenecks, operational failures, and reliability issues in high-throughput production environments. Apply reliability engineering principles to minimize service disruptions and maintain consistent performance under real-world workloads. Ensure system correctness, resilience, and operational stability in environments with demanding latency and availability requirements. Cross-Functional Collaboration and Technical Leadership Partner with agent systems engineers, machine learning specialists, and infrastructure teams to define and deliver production-ready solutions. Translate experimental requirements into scalable architectures and maintainable engineering implementations. Contribute to technical design discussions, infrastructure standards, and engineering best practices. Take ownership of critical production systems, proactively identifying risks and driving improvements throughout the software lifecycle. Support the evolution of the AI infrastructure platform as product requirements, workloads, and business needs grow. Requirements At least five years of experience building, deploying, and operating high-scale production software systems. Strong proficiency in Rust and systems-level programming, with the ability to develop efficient, reliable, and maintainable services. Deep understanding of distributed systems, including service communication, concurrency, fault tolerance, and reliability engineering. Proven experience optimizing system performance, particularly latency, throughput, resource utilization, and operational efficiency. Experience operating services that support millions of users or handle high-throughput workloads in production. Familiarity with machine learning infrastructure, model serving, or MLOps practices in production environments. Experience designing and implementing observability solutions, including monitoring, logging, tracing, alerting, and failure recovery. Strong understanding of production operations, incident investigation, system resilience, and performance troubleshooting. Ability to collaborate effectively across infrastructure, applied engineering, and AI-focused teams to deliver complex technical solutions. Strong ownership and accountability, with the ability to make sound technical decisions and manage critical systems in high-stakes environments. Excellent analytical and problem-solving skills, with a systematic approach to diagnosing failures and improving system behavior. Clear technical communication skills and the ability to contribute to architectural discussions and cross-functional engineering initiatives. Nice to have: Experience building infrastructure for AI agents, autonomous workflows, or large language model (LLM)-powered applications. Background in high-performance networking, asynchronous systems, or low-latency architectures. Experience with container orchestration, cloud-native infrastructure, and modern deployment platforms. Familiarity with model evaluation frameworks, inference benchmarking, and monitoring model performance at scale. Experience building new platforms or foundational systems in fast-moving environments, particularly during early-stage development and the transition from prototype to production. Benefits Employment type: Full-time position. Work arrangement: Fully remote, with Brazil included among the eligible hiring locations. Competitive compensation: Salary and compensation details are not specified in the original job description. High-impact engineering: Opportunity to build foundational AI infrastructure supporting intelligent systems at significant scale. Technical ownership: Direct involvement in architectural decisions, infrastructure design, and production engineering. Advanced technology environment: Hands-on work with Rust, distributed systems, AI agent infrastructure, model serving, and performance optimization. Cross-functional collaboration: Work alongside specialists in AI, machine learning, agent systems, and infrastructure engineering. Professional development: Exposure to emerging AI infrastructure practices, production MLOps, and complex distributed systems challenges. Engineering excellence: An environment that emphasizes reliability, observability, scalability, operational correctness, and continuous improvement. Global collaboration: Opportunities to work with distributed engineering teams across multiple regions.