AI Engineer

Niuro; Brasil; Teletrabalho; BRL 300 000 - 540 000; Tempo integral

Resumo da oferta

Niuro is seeking a Senior AI Engineer to design, develop, and deploy production-ready AI solutions. You will build scalable applications leveraging LLMs, RAG, AI agents, and related technologies, turning experiments into reliable APIs and services. You will own AI features end-to-end, collaborate with product and engineering teams, implement observability, and mentor others on AI topics while exploring new frameworks and deployment patterns.

Qualificações

• 4+ years in AI/ML with production-grade software delivery.
• Hands-on with LLMs such as OpenAI, Claude, Mistral, or open-source models.
• Experience with AI agent frameworks and RAG architectures.
• Strong Python and API development with FastAPI, Django, or similar.
• Cloud deployment on AWS, GCP, or Azure.
• Experience with Docker, Kubernetes, and Terraform.
• Familiar with LangChain and Transformers.

Responsabilidades

• Design LLM-based solutions including RAG systems and AI agents.
• Fine-tune, evaluate, and deploy foundation models.
• Build end-to-end AI-powered features with product teams.
• Develop scalable APIs and services for AI capabilities.
• Own AI features from experimentation to deployment and monitoring.
• Collaborate with DevOps on CI/CD and IaC for AI services.
• Implement observability and performance monitoring for AI systems.
• Evaluate AI frameworks and emerging technologies.
• Contribute to AI architecture discussions and best practices.
• Mentor engineers on AI topics and knowledge sharing.
• Identify opportunities to apply AI to products and business solutions.

Conhecimentos

LLMs

AI/ML production

Python

APIs

CI/CD

Observability

Mentoring

Prompt engineering

Ferramentas

LangChain

Transformers

Docker

Kubernetes

Terraform

FastAPI

OpenAI

Descrição da oferta de emprego

An experienced Senior AI Engineer is needed to design, develop, and deploy production-ready AI solutions. This role focuses on building scalable applications utilizing Large Language Models (LLMs), intelligent agents, Retrieval-Augmented Generation (RAG) systems, and AI-driven features. The position demands a strong combination of AI expertise and robust software engineering practices to transition experimental models into reliable, production-grade APIs and services.Operating with a high degree of autonomy, the engineer will collaborate closely with engineering and product teams to own the lifecycle of AI features from prototyping to deployment and monitoring. This role is critical for establishing best practices in AI architecture, implementing observability, and mentoring other engineers on AI-related topics.

Responsibilities

• Design and implement LLM-based solutions, including RAG systems, AI agents, copilots, and other generative AI applications.
• Fine-tune, evaluate, and deploy both proprietary and open-source foundation models.
• Build end-to-end AI-powered features in collaboration with product and engineering teams.
• Develop scalable APIs and services to integrate AI capabilities into applications.
• Own the lifecycle of AI features, from experimentation and prototyping through deployment and monitoring.
• Collaborate with DevOps and engineering teams on CI/CD and infrastructure-as-code for AI services.
• Implement observability, error tracking, and performance monitoring for AI-powered systems.
• Evaluate and experiment with AI frameworks, libraries, and emerging technologies.
• Contribute to technical discussions around AI architecture and best practices.
• Support knowledge sharing and mentor other engineers on AI-related topics.
• Identify opportunities to incorporate AI into products and business solutions.

Requirements

• Senior-level experience with 4+ years of experience working in AI/ML-focused roles and delivering software products to production.
• Hands-on experience working with LLMs, including models such as OpenAI, Claude, Mistral, or open-source alternatives.
• Experience with AI agent frameworks and 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 such as AWS, GCP, or Azure.
• Experience with technologies such as Docker, Kubernetes, and Terraform.
• Strong software engineering fundamentals, including testing, code reviews, Git, modular design, and maintainable code.
• Experience deploying, monitoring, and maintaining AI systems in production.
• Hands-on experience with LangChain, Transformers.