AI Engineer

🌟What are we looking for?

• Experience in developing solutions based on Generative Artificial Intelligence.
• Solid knowledge of LLMs and applications based on generative models.
• Experience in RAG architectures and information retrieval systems.
• Experience in the design and development of AI agents.
• Knowledge of MCP (Model Context Protocol) or tool-based architectures.
• Experience with frameworks such as LangGraph, Google ADK, or similar.
• Experience in integrating APIs, services, and various information sources.
• Proficiency in Python for the development of AI-oriented services and solutions.
• Analytical skills, autonomy, and a problem-solving mindset.

🔝Anything else to add value?

We will positively value:

• Experience with Langfuse, LangSmith, or other observability tools for LLM applications.
• Knowledge of vector databases and hybrid search.
• Experience in the evaluation and optimization of RAG systems and agents.
• Knowledge of Prompt Engineering and advanced context management.
• Experience with distributed architectures, APIs, and microservices.
• Knowledge of Docker, Kubernetes and the deployment of AI solutions in production.
• Experience evaluating models and making technical decisions based on impact, quality, and cost.
• English level.

Are you passionate about Generative Artificial Intelligence? Do you enjoy facing complex problems and transforming them into real solutions? We are looking for you!

At Nunsys Group, we continue to expand our AI team and are looking to hire an AI Engineer to participate in the design, development, and evolution of solutions based on Generative Artificial Intelligence.

Your mission will be to design and build generative AI solutions capable of solving real business problems, participating in the entire solution lifecycle, from research and technical validation to its deployment and evolution in production.

You will participate in projects where LLMs, RAG systems, and AI agents form a central part of the architecture, collaborating in roles such as:

• Designing and developing applications and agents based on Large Language Models (LLMs).
• Building and optimizing RAG (Retrieval-Augmented Generation) architectures.
• Designing agents and workflows using technologies such as LangGraph, Google ADK, or similar frameworks.
• Integrating models and agents with tools, services, and data sources through MCP (Model Context Protocol).
• Evaluating different models, architectures, and technologies to select the best solution in each case.
• Designing evaluation strategies to measure the quality, accuracy, and behavior of AI systems.
• Analyzing metrics related to performance, latency, scalability, and costs.
• Participating in the observability and monitoring of applications using tools such as Langfuse, LangSmith or similar.
• Collaborating with technical and product teams to transform business needs into applicable solutions in real environments.
• Participating in the continuous improvement of platforms and products based on Artificial Intelligence.

We are looking for an autonomous, curious person with technical judgment, capable of asking questions such as:

• Why use this architecture and not another?
• How can we measure if it truly adds value?
• What is the impact on quality, latency, and cost?
• What deserves optimization and what does not?

We are interested in someone with the capacity to experiment, learn constantly, and convert promising ideas into robust solutions for production environments.