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 manage intricate integrations between systems utilizing REST/GraphQL APIs, API Gateways, and Load Balancers.

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

• Design, enhance, and uphold Agentic AI architectures along with Agent-to-Agent (A2A) communication.

• Implement and support integrations with MCP (Model Context Protocol).

• Refine and maintain OCR pipelines and unstructured data extraction using LLMs.

• Create, oversee, and advance monitoring and observability dashboards employing Grafana, Rancher, and related tools.

• Monitor and optimize AI applications in production to ensure scalability, stability, and operational efficiency.

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

• Collaborate with multidisciplinary teams across engineering, data, architecture, and product domains.

⛳️ Requirements

• Strong proficiency in backend development using 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.

• Familiarity with integration via REST/GraphQL APIs.

• Advanced understanding of API Gateway, Load Balancer, and distributed architectures.

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

• Proficient with Grafana, Datadog, ELK Stack, or similar tools.

• Practical knowledge of LangChain, LangFlow, and LangGraph.

• Experience with Agentic AI and A2A communication processes.

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

• Familiarity with OCR, document processing, and unstructured data extraction techniques.

• Experience with CI/CD, DevOps, and/or MLOps methodologies.

• Proficiency with Git and automated deployment pipelines.

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

• Nice to have: Java and Spring Boot knowledge; experience with CrewAI, AutoGen or similar frameworks; familiarity with RAG; vector databases and embeddings; OpenAI API, Anthropic or other LLM providers; AWS Textract, Tesseract or other OCR tools; exposure to high-volume environments and mission-critical applications; consultancy experience or experience in fast-evolving technology contexts.

• Analytical mindset focused on solving intricate problems.

• Strong communication skills with the ability to collaborate closely with both technical and business teams.

• Ability to work collaboratively in multidisciplinary environments.

• Hands-on approach, autonomy, and a strong sense of responsibility.

• Capable of functioning in dynamic environments with multiple simultaneous challenges.

• Ongoing interest in learning and advancing in AI technologies.

• Skill in prioritizing and organizing tasks in critical situations.

• Architectural insight with a focus on scalability, stability, and technical governance.

🏝️ Benefits

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

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

• Birthday – gift voucher and an additional day off.

• Full access to RoxSchool, Alura platform, Pluralsight, and O'Reilly for books and talks.

• Certification reimbursement up to R$300.00 (TECHNOLOGY) + R$300.00 bonus for each certification achieved from these brands.

• Psychological support – two psychotherapy sessions funded monthly by ROX.

• Feedz partnership – a gamified platform for communication, sentiment, engagement, feedback, PDI, and performance management.

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

• Work equipment provided.