This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a AI Engineer – Generative AI & AWS based in Brazil.
This is a senior, hands-on engineering role focused on building and deploying advanced Generative AI solutions within a production-grade cloud environment. You will work on the design and implementation of LLM-powered applications, AI agents, and API-driven workflows that support complex business needs in a regulated industry. The role combines strong software engineering foundations with applied AI expertise, particularly around orchestration frameworks, AWS services, and scalable cloud architectures. You will contribute to building intelligent systems that integrate seamlessly with enterprise workflows, ensuring reliability, security, and performance. The environment is highly technical, international, and collaborative, requiring autonomy, precision, and strong communication skills. This is an opportunity to work on cutting-edge AI initiatives with real-world impact in a mission-critical domain.
Accountabilities:
- Design, develop, and deploy Generative AI solutions leveraging Large Language Models and modern AI frameworks.
- Build and maintain AI Agent workflows, orchestration pipelines, and LLM-based applications for business use cases.
- Develop and integrate APIs using Python to connect AI systems with internal and external platforms.
- Architect and manage cloud-based AI infrastructure on AWS, ensuring scalability, security, and reliability.
- Implement and support production-ready AI applications using CI/CD pipelines, Docker, and Kubernetes.
- Work with vector databases, RAG pipelines, embeddings, and retrieval strategies to enhance AI system performance.
- Collaborate with technical teams and stakeholders to gather requirements and deliver robust AI-driven solutions.
- Participate in technical discussions, solution design, and client-facing communications when required.
- Troubleshoot, optimize, and continuously improve deployed AI systems and workflows.
- Contribute to engineering best practices, documentation, and system observability.
Requirements:
- 3+ years of experience in Software Engineering, AI Engineering, Machine Learning Engineering, or Cloud Engineering roles.
- At least 2+ years of hands-on experience with Generative AI, LLMs, or AI Agent frameworks.
- Strong proficiency in Python for backend development and AI system integration.
- Proven experience building and integrating APIs in production environments.
- Hands-on experience with AWS cloud services and infrastructure.
- Familiarity with LLM ecosystems such as OpenAI, Claude, Llama, or AWS Bedrock.
- Experience with AI orchestration tools such as LangChain, LangGraph, CrewAI, AutoGen, or similar.
- Solid understanding of RAG architectures and vector databases.
- Experience with CI/CD pipelines, Docker, and Kubernetes.
- Strong knowledge of Git and modern software development workflows.
- Advanced English and Spanish communication skills.
- Availability to work aligned with U.S. business hours from Latin America.
- Strong problem-solving mindset with the ability to work independently in complex environments.
- Experience in regulated industries such as insurance, fintech, or healthcare is a plus.
Benefits:
- 100% remote contractor opportunity based in Latin America.
- Work directly with a U.S.-based insurance organization on mission-critical AI initiatives.
- Exposure to advanced Generative AI, LLM, and AI Agent development at scale.
- Hands-on experience with AWS-native AI architectures and cloud infrastructure.
- International, English-speaking, highly technical work environment.
- Opportunity to build and deploy real-world AI systems in a regulated enterprise setting.
- Participation in cutting-edge projects involving next-generation AI engineering practices.