Senior AI Engineer (LLMs / RAG / AI Agents)

4+ years in AI/ML-focused roles delivering software products to production.

Hands-on experience with LLMs (OpenAI, Claude, Mistral or open-source alternatives).

Experience with AI agent frameworks and/or agentic architectures.

Strong knowledge of prompt engineering, embeddings and vector databases.

Experience designing and implementing RAG architectures.

Experience testing and evaluating AI systems and LLM-powered applications.

Strong Python skills and experience building APIs with FastAPI, Django or similar frameworks.

Production experience with at least one major cloud platform (AWS, GCP or Azure).

Experience with Docker, Kubernetes and Terraform.

Solid software engineering fundamentals: testing, code reviews, Git, modular design and maintainable code.

Experience deploying, monitoring and maintaining AI systems in production.

Hands-on experience with LangChain and Transformers.

Ability to work autonomously and communicate effectively with both technical and non-technical stakeholders.

Professional English.

You'll join an AI & Data team as a senior engineer, working independently while collaborating closely with engineering and product teams. You'll design and implement LLM-based solutions such as RAG systems, AI agents, copilots and other generative AI applications.

You'll fine-tune, evaluate and deploy both proprietary and open-source foundation models, and build scalable APIs and services that integrate AI into applications. You'll own the full lifecycle of AI features, from experimentation and prototyping through deployment and monitoring.

You'll work with DevOps on CI/CD and infrastructure as code, and implement observability, error tracking and performance monitoring for AI systems. You'll also contribute to AI architecture discussions, share knowledge and mentor other engineers, and look for new opportunities to bring AI into products.

Success means going beyond prototypes: reliable, observable AI features running in production and delivering real business value.

MLOps practices and model deployment workflows.

AI evaluation and testing tools such as Promptfoo, Giskard or similar.

Experience with multi-agent systems.

Experience identifying and implementing AI use cases within digital products.

00% remote position for candidates based in Latin America (Brazil, Argentina, Uruguay and Colombia preferred).

Full-time, direct hire with the client company.

Flexible working schedule.

Continuous learning and professional development opportunities.

Access to modern AI technologies and development tools.

Collaboration with experienced professionals across different technical disciplines.

Challenging AI projects and production-grade solutions.

Selection process: HR Interview → Technical Challenge → Technical Interview → Offer.