AI Engineer Senior

Jobgether; Brasil; Sur place; BRL 250 000 - 420 000; Plein temps

Avantages offerts par ce poste

Health and dental insurance

Meal allowances

Childcare assistance

Extended paternity leave

Wellness partnerships

Profit-sharing program

Life insurance

Continuous learning

Online learning partnerships

Language learning

Discount club

Well-being resources

Parenting support

Inclusive workplace

Accessibility and accommodations

Résumé du poste

Jobgether is seeking a Senior AI Engineer based in Brazil to design, build, and deploy production-ready AI applications using large language models and foundation models. You will develop retrieval-augmented generation pipelines, multi-agent systems, and scalable AI architectures, collaborating with product managers, data scientists, and engineers.

You will optimize models, ensure observability, and drive experimentation with emerging AI technologies while delivering reliable, business-focused

Qualifications

• Significant professional experience in software engineering and building production-grade AI solutions.
• Hands-on experience with LLMs, foundation models, and associated APIs.
• Practical experience with agentic architectures using LangChain, LlamaIndex, CrewAI, or OpenGen.
• Strong knowledge of prompt engineering, optimization, and model performance.
• Familiarity with vector databases and embedding models for knowledge networks.

Responsabilités

• Design, develop, and deploy production-ready AI applications powered by LLMs.
• Architect and optimize RAG pipelines for large-scale document retrieval.
• Implement multi-agent AI systems using Bedrock Agents and related frameworks.
• Build backend services and APIs in Python; ensure scalability and reliability.
• Develop monitoring, observability, and cost-management for AI systems.
• Collaborate with cross-functional teams to translate business needs into technical solutions.

Connaissances

Python

LangChain

LlamaIndex

CrewAI

AutoGen

AWS Bedrock

OpenAI SDK

Gemini

DevOps

Outils

Pinecone

Weaviate

OpenSearch

Description du poste

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

Join a technology-driven environment where generative AI, software engineering, and business innovation come together to solve complex challenges. As a Senior AI Engineer, you will design, build, and deploy production-ready AI applications that help organizations unlock the full potential of artificial intelligence. You will work with leading foundation models and cloud platforms to develop advanced retrieval-augmented generation (RAG) pipelines, intelligent agents, and scalable AI architectures. Collaborating with product managers, data scientists, architects, and engineers, you will turn business requirements into reliable, high-impact solutions. Beyond implementation, you will contribute to model optimization, system observability, and continuous experimentation with emerging AI technologies. This role is ideal for an experienced engineer who combines strong software development skills with practical expertise in generative AI and agentic systems.

Accountabilities:

• Design, develop, and deploy production-ready applications powered by large language models (LLMs), including GPT, Gemini, Claude, and other foundation models through platforms such as AWS Bedrock.
• Architect, build, and optimize advanced retrieval-augmented generation (RAG) pipelines capable of processing and retrieving information from large-scale document repositories.
• Implement and orchestrate multi-agent AI systems using AWS Bedrock Agents, AgentCore, and relevant agentic frameworks.
• Develop scalable AI pipelines and integrate them with enterprise systems while maintaining performance, reliability, and operational efficiency.
• Build robust backend services and APIs for AI applications using Python and modern development frameworks.
• Implement containerization, deployment strategies, and infrastructure practices that support reliable AI application delivery.
• Develop monitoring and observability solutions to measure AI system performance, response quality, reliability, and operational costs.
• Design and refine prompts, templates, and advanced prompt engineering techniques to improve model behavior, accuracy, and consistency.
• Evaluate and fine-tune models for specific use cases when appropriate, experimenting with configurations, hyperparameters, and architectural approaches.
• Collaborate with product managers, data scientists, solution architects, engineers, and business stakeholders to translate complex requirements into effective technical solutions.
• Stay informed about developments in generative AI research and assess emerging models, frameworks, and technologies for practical applications.
• Contribute to technical documentation, engineering standards, best practices, and knowledge-sharing initiatives.
• Participate in sales-related initiatives involving generative AI, helping communicate technical capabilities and potential solutions.

Requirements:

The ideal candidate will have substantial software engineering experience, strong programming skills, and hands‑on expertise in designing and delivering generative AI solutions. Relevant qualifications and capabilities include:

• Significant professional experience in software engineering, ideally involving the development of complex, production-grade applications.
• Full-stack development experience and the ability to work across backend services, APIs, and application integrations.
• Hands‑on experience with large language models, foundation models, and associated APIs.
• Practical experience designing and implementing agentic architectures using frameworks such as LangChain, LlamaIndex, CrewAI, or AutoGen.
• Strong knowledge of prompt engineering, prompt optimization, and techniques for improving LLM performance and output quality.
• Experience building retrieval and knowledge systems for AI agents using vector databases such as Pinecone, Weaviate, or OpenSearch, along with embedding models or knowledge graphs.
• Proficiency in Python and familiarity with modern frameworks and libraries used to develop AI-powered applications.
• Experience with cloud-based AI platforms, particularly AWS Bedrock, and familiarity with models and services such as OpenAI SDK and Gemini.
• Understanding of DevOps practices, containerization, and CI/CD pipelines for deploying and maintaining AI applications.
• Ability to design scalable, maintainable, and reliable AI systems that integrate with enterprise environments.
• Strong analytical and problem-solving skills, with the ability to evaluate alternative models and architectures and make informed technical decisions.
• Excellent collaboration and communication skills, including the ability to work with multidisciplinary teams and translate business needs into technical solutions.
• A proactive approach to continuous learning, experimentation, documentation, and knowledge sharing.

Benefits:

• Health and dental insurance: Access to healthcare coverage.
• Meal and food allowances: Financial support for meals and food expenses.
• Childcare assistance: Support for eligible childcare needs.
• Extended paternity leave: Additional time to support family life and parenting.
• Wellness partnerships: Access to gyms and health and wellness professionals through platforms such as Wellhub (Gympass) and TotalPass.
• Profit-sharing program: Participation in Profit Sharing and Results Participation (PLR).
• Life insurance: Coverage to support financial protection.
• Continuous learning: Access to a dedicated learning platform through CI&T University.
• Online learning partnerships: Opportunities to develop technical and professional skills through external learning platforms.
• Language learning: Access to a language learning platform.
• Discount club: Access to partner discounts and special offers.
• Well-being resources: A free online platform focused on physical, mental, and overall well-being.
• Parenting support: Access pregnancy and responsible parenting courses.
• Inclusive workplace: Support from dedicated health and well-being teams, inclusion specialists, and affinity groups.
• Accessibility and accommodations: Support for candidates with disabilities throughout the recruitment process, including assistance with obtaining the necessary assessment documentation where needed.