AI Ops Engineer – Backend Developer, Python

Rox Partner

Engenheiro AI Ops desenvolvendo backend Python e aplicações de IA generativa para a consultoria de dados Rox Partner. Operação em AWS, observabilidade, OCR, Agentic AI e integrações distribuídas.

Posted 8/20/2026full-timeRemote • 🇧🇷 BrazilMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in deploying and maintaining AI applications in high-availability environments, with strong capabilities in backend development using Python and cloud infrastructure on AWS. Proficient in integrating systems via REST/GraphQL APIs and optimizing AI architectures for performance and scalability.

Highest-signal resume keywords

Backend Development with PythonAWS Cloud InfrastructureGenerative AI Application DeploymentMonitoring and Observability with GrafanaAPI Integration and Management

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

PythonFastAPIFlaskDjangoREST APIsGraphQL APIsMCP (Model Context Protocol)OCRCI/CDDevOps

Soft Skills

Analytical Problem SolvingGood CommunicationCollaboration in Multidisciplinary TeamsAutonomy and ResponsibilityAbility to Prioritize and Organize

Tools & Technologies

AWSGrafanaDatadogELK StackRancherLangChainLangFlowLangGraphLoad BalancerAPI Gateway

Industry Keywords

AI ApplicationsAgentic AIA2A CommunicationUnstructured Data ExtractionHigh-Availability EnvironmentsProduction TroubleshootingMission-Critical ApplicationsDynamic EnvironmentsContinuous Learning in AI TechnologiesTechnical Governance

Tech Stack

Tools & technologies

AWSCloudDjangoFlaskGrafanaGraphQLJavaPythonSpringSpring BootSpringBoot

About the role

Key responsibilities & impact

Deploy, orchestrate, and maintain AI applications in high-availability production environments
Develop and maintain complex integrations between systems using REST/GraphQL APIs, API Gateways, and Load Balancers
Build data pipelines and processing flows for AI applications using Python on AWS
Design, optimize, and maintain Agentic AI architectures and Agent-to-Agent (A2A) communication
Implement and support integrations with MCP (Model Context Protocol)
Evolve and maintain OCR pipelines and unstructured data extraction using LLMs
Create, manage, and evolve monitoring and observability dashboards with Grafana, Rancher, and related tools
Monitor and optimize AI applications in production, ensuring scalability, stability, and operational efficiency
Identify and resolve performance issues, bottlenecks, and failures in AI pipelines
Collaborate with multidisciplinary teams in engineering, data, architecture, and product

Requirements

What you’ll need

Strong experience in backend development with Python (FastAPI, Flask, Django or similar)
Deep experience with AWS and cloud infrastructure services
Hands-on experience deploying and supporting Generative AI applications in production
Experience integrating via REST/GraphQL APIs
Advanced knowledge of API Gateway, Load Balancer, and distributed architectures
Experience with monitoring, observability, and production troubleshooting
Experience with Grafana, Datadog, ELK Stack or similar
Practical knowledge of LangChain, LangFlow and LangGraph
Experience with Agentic AI and A2A communication flows
Knowledge and implementation experience with MCP (Model Context Protocol)
Experience with OCR, document processing and unstructured data extraction
Experience with CI/CD, DevOps and/or MLOps
Experience with Git and automated deployment pipelines
Knowledge of containers, clusters and management via Rancher
Nice to have: Java and Spring Boot; CrewAI, AutoGen or similar frameworks; RAG; vector databases and embeddings; OpenAI API, Anthropic or other LLM providers; AWS Textract, Tesseract or other OCR tools; high-volume environments and mission-critical applications; consultancy experience or fast-evolving technology environments
Analytical profile and focused on solving complex problems
Good communication and ability to work closely with technical and business areas
Ability to work collaboratively in multidisciplinary teams
Hands-on profile, autonomy and a sense of responsibility
Ability to operate in dynamic environments with multiple simultaneous challenges
Continuous interest in learning and evolving in AI technologies
Ability to prioritize and organize in critical environments
Architectural vision and concern for scalability, stability and technical governance

Benefits

Comp & perks

Remote work – Monday to Friday (09:00–18:00)
Home-office allowance – iFood card credit for Meal/Food worth R$ 300.00 per month
Birthday – gift voucher and a 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 per certification achieved from these brands
Psychological support – two psychotherapy sessions covered monthly by ROX
Feedz partnership – gamified platform for communication, sentiment, engagement, feedback, PDI and performance
WellHub (Gympass) – partnerships with gyms and health & wellness apps
Work equipment provided