Job Description

We are looking for an engineer to contribute to the development of Nexum products based on generative AI, software agents and intelligent automation. The role involves working on applications that use LLMs, agent orchestration, inference pipelines, RAG, tool calling, output evaluation and integration with enterprise systems. Tech Stack: Python, TypeScript, FastAPI, React, Docker, LLM APIs, vector DB, LangGraph/LangChain, open-weight models like Llama, Qwen, Mistral, Gemma, DeepSeek and Phi. Key Responsibilities: - Develop and maintain AI products based on LLMs and software agents - Design inference pipelines, RAG and tool calling systems - Integrate AI models with existing enterprise systems - Evaluate and optimize model outputs - Collaborate with the team to define scalable architectures - Contribute to research and experimentation with new AI approaches This job posting is addressed to both genders, in compliance with laws 903/77 and 125/91 on equal treatment in the workplace and against gender discrimination. We welcome candidates of all ages and nationalities, in accordance with legislative decrees 215/03 and 216/03. Nexum also encourages applications from people with disabilities, in compliance with current regulations.

Requirements

• AI & LLM

  Experience with LLMs, RAG, tool calling, agent orchestration (LangGraph/LangChain)

• Tech Stack

  Python, TypeScript, FastAPI, React, Docker, vector DB

• Open-Weight Models

  Familiarity with Llama, Qwen, Mistral, Gemma, DeepSeek, Phi

• Enterprise Integration

  Ability to integrate AI solutions into complex enterprise systems