AI Ops Engineer – Backend Developer, Python

This is a fully remote position, open to applicants in Brazil.

📋 Description

• Deploy, orchestrate, and sustain AI applications within high-availability production settings.

• Develop and uphold intricate system integrations utilizing REST/GraphQL APIs, API Gateways, and Load Balancers.

• Construct data pipelines and processing workflows for AI applications using Python in AWS environments.

• Design, optimize, and support architectures centered around Agentic AI and Agent-to-Agent (A2A) communication.

• Implement and facilitate integrations utilizing MCP (Model Context Protocol).

• Evolve and maintain OCR pipelines and workflows for unstructured data extraction employing LLMs.

• Create, manage, and enhance sophisticated monitoring and observability dashboards to ensure model health, inference performance, application availability, and control over operational costs using Grafana, Rancher, and related tools.

• Oversee and optimize AI applications in production to guarantee scalability, stability, and operational efficiency.

• Identify and rectify performance issues, bottlenecks, and failures within AI pipelines.

• Collaborate with cross-functional teams in engineering, data, architecture, and product domains.

⛳️ Requirements

• Strong expertise in backend development with Python (FastAPI, Flask, Django, or similar frameworks).

• Extensive experience with AWS and cloud infrastructure services.

• Practical experience in deploying and supporting Generative AI applications in production environments.

• Experience in integrations through REST/GraphQL APIs.

• Advanced understanding of API Gateways, Load Balancers, and distributed architectures.

• Experience in monitoring, observability, and troubleshooting within production settings.

• Familiarity with tools such as Grafana, Datadog, ELK Stack, or similar platforms.

• Hands-on knowledge of LangChain, LangFlow, and LangGraph.

• Experience with Agentic AI and A2A communication flows.

• Knowledge and practical experience with MCP (Model Context Protocol).

• Experience in OCR, document processing, and unstructured data extraction techniques.

• Familiarity with CI/CD, DevOps, and/or MLOps practices.

• Proficiency with Git and automated deployment pipelines.

• Understanding of containers, clusters, and management through Rancher.

🏝️ Benefits

• Remote work – Monday to Friday (09:00–18:00).

• Home-office allowance – Credit on iFood card for meals/food worth R$ 300.00 per month.

• Birthday – Rox gifts you a voucher and a day off to celebrate your special day.

• Courses – Full access to RoxSchool, Alura, Pluralsight, and O'Reilly (books and talks).

• Certifications – Reimbursement of up to R$ 300.00 for technology certifications, plus a R$ 300.00 bonus for each certification achieved from these providers.

• Psychologist support – Two psychotherapy sessions covered monthly by ROX with partner psychologists.

• Feedz partnership – A gamified platform to enhance connectivity, improve communication, and monitor sentiments, engagement, feedback, development plans (PDI), and performance.

• WellHub (Gympass) – Partnership with gyms and health and wellness applications.

• Work equipment provided.