Senior - AI Deployment Engineer

Jobgether; Brasil; On-site; BRL 250,000 - 350,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Meal allowances

Childcare assistance

Extended paternity leave

Wellness partnerships

Profit sharing

Life insurance

Learning platform

Discount club

Job summary

Jobgether seeks a Senior AI Deployment Engineer based in Brazil to lead end-to-end deployment of AI-powered solutions, combining DevOps, SRE, and LLMOps to ensure secure, observable and cost-efficient production. You will design pipelines, automate infrastructure, and govern model serving across environments.

Your work will emphasize reliability, scalability, and responsible AI practices, with strong collaboration across AI delivery teams to optimize costs and performance.

Qualifications

• LLMOps deployment and operation of large language models and AI systems.
• Strong DevOps practices including infrastructure automation, deployment management, and CI/CD.
• Understanding of SRE, reliability, availability, performance, and scalability.
• Experience with AI security, access control, and production data protection.
• Familiarity with observability and monitoring for applications and AI systems.
• Understanding of AI FinOps, inference cost management, and optimization techniques.
• Knowledge of infrastructure guardrails and AI safety to mitigate risks.
• Experience with CI/CD processes.
• Understanding of model routing and selection strategies to optimize performance and cost.
• Ability to manage production environments, release processes, versioning, and incident recovery.

Responsibilities

• Design and manage CI/CD pipelines for agentic environments, reducing the time between solution development and production delivery.
• Deploy conventional applications across platforms and distribution channels, including app stores, CDNs, mobile release trains, feature flags, and blue/green service rollouts.
• Provision, automate, and maintain standardized development, staging, and production environments.
• Operate and manage model and AI agent serving infrastructure, ensuring production availability, performance, low latency, and scalability.
• Establish quality, security, and compliance gates throughout the delivery pipeline to validate solutions before release.
• Define and manage versioning strategies, release schedules, rollback procedures, and rapid recovery processes in case of production failures.
• Implement observability and monitoring for AI solutions, tracking system behavior, operational health, solution quality, performance, and token consumption.
• Manage AI FinOps activities by monitoring and optimizing inference costs, managing budgets, and implementing intelligent model routing to balance cost and performance.
• Secure production environments through access controls, data protection measures, and mitigation of AI-related risks, ensuring compliance with client requirements.
• Implement infrastructure guardrails to manage model risk and prevent inappropriate or unsafe agent behavior in production.
• Manage versioning and traceability for application packages, environment configurations, and model endpoints to support controlled releases and safe rollbacks.
• Share production insights with upstream engineering teams, particularly regarding costs, failures, and real-world performance, to support continuous solution optimization.
• Apply responsible AI, ethics, privacy, data security, and compliance practices throughout deployment and production operations.

Skills

LLMOps

DevOps

SRE

CI/CD

Observability

AI FinOps

Security & Compliance

Model routing

Incident recovery

Versioning & releases

Tools

Terraform

Kubernetes

Azure Container Apps

IaC

Job description

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior - AI Deployment Engineer based in Brazil.

The Senior AI Deployment Engineer will lead the transition of AI-powered solutions from development into secure, reliable, and cost-efficient production environments. This role combines DevOps, Site Reliability Engineering (SRE), and LLMOps practices to support the deployment and operation of both conventional applications and advanced AI systems. You will design CI/CD pipelines, automate infrastructure, manage model serving, and establish release and recovery strategies for agentic environments. A key focus will be ensuring production systems remain observable, scalable, secure, and economically sustainable. Working across deployment and AI engineering activities, you will use operational insights to continuously improve delivery performance and solution quality.

Accountabilities:

• Design and manage CI/CD pipelines for agentic environments, reducing the time between solution development and production delivery.


• Deploy conventional applications across platforms and distribution channels, including app stores, content delivery networks (CDNs), mobile release trains, feature flags, and blue/green service rollouts.


• Provision, automate, and maintain standardized development, staging, and production environments.


• Operate and manage model and AI agent serving infrastructure, ensuring production availability, performance, low latency, and scalability.


• Establish quality, security, and compliance gates throughout the delivery pipeline to validate solutions before release.


• Define and manage versioning strategies, release schedules, rollback procedures, and rapid recovery processes in case of production failures.


• Implement observability and monitoring for AI solutions, tracking system behavior, operational health, solution quality, performance, and token consumption.


• Manage AI FinOps activities by monitoring and optimizing inference costs, managing budgets, and implementing intelligent model routing to balance cost and performance.


• Secure production environments through access controls, data protection measures, and mitigation of AI-related risks, ensuring compliance with client requirements.


• Implement infrastructure guardrails to manage model risk and prevent inappropriate or unsafe agent behavior in production.


• Manage versioning and traceability for application packages, environment configurations, and model endpoints to support controlled releases and safe rollbacks.


• Share production insights with upstream engineering teams, particularly regarding costs, failures, and real-world performance, to support continuous solution optimization.


• Apply responsible AI, ethics, privacy, data security, and compliance practices throughout deployment and production operations.

Requirements:

• Strong experience or technical expertise in LLMOps, including the deployment and operation of large language models and AI-powered systems.


• Knowledge of DevOps engineering practices, including infrastructure automation, deployment management, and CI/CD.


• Understanding of Site Reliability Engineering (SRE), production reliability, availability, performance, and scalability.


• Experience or knowledge of AI security, access control, and production data protection.


• Familiarity with observability and monitoring practices for application and AI systems.


• Understanding of AI FinOps, inference cost management, and cost optimization techniques.


• Knowledge of infrastructure guardrails, AI safety, and approaches to mitigating risks associated with AI models and agents.


• Experience with continuous integration and continuous delivery (CI/CD) processes.


• Understanding of model routing and selection strategies to optimize performance and operational costs.


• Ability to manage production environments, release processes, versioning, and incident recovery.


• Strong problem-solving and collaboration skills, with the ability to communicate operational findings and work closely with AI engineering and delivery teams.

Nice to have:

• Knowledge of cloud computing concepts and architectures.


• Practical experience with Infrastructure as Code (IaC), particularly Terraform.


• Familiarity with Azure Container Apps.


• Understanding of scalability and connectivity considerations in distributed environments.


• Experience with code reviews and software quality practices.


• Knowledge of Kubernetes (K8s) and container-based infrastructure.

Benefits:

• Health and dental insurance.


• Meal and food allowances.


• Childcare assistance.


• Extended paternity leave.


• Access to gym, fitness, and wellness partnerships through Wellhub (Gympass) and TotalPass.


• Profit Sharing and Results Participation (PLR).


• Life insurance.


• Continuous learning opportunities through an internal learning platform.


• Discounts through a partner discount club.


• Free online resources dedicated to physical, mental, and overall well-being.


• Pregnancy and responsible parenting courses.


• Partnerships with online learning platforms.


• Access to a language-learning platform.


• Additional employee benefits and well-being initiatives.