• •AI Visionary : Lead the Development of Advanced Language Model Capabilities • •

beBeeLanguage; Madrid; Híbrido; EUR 50.000 - 70.000; Jornada completa

Descripción de la vacante

A technology company specializing in AI located in Madrid is looking for an experienced software engineer to develop LLM-powered applications. The role involves working with AI technologies and requires strong expertise in Python, deep learning frameworks, and LLM APIs. The company offers competitive salary, hybrid work options, and a supportive team environment.

Servicios

Competitive salary

Startup equity

Generous time off

Flexible hours

Top-notch tech and gear

Formación

• 5+ years of experience in software engineering focused on AI and ML.
• Expert-level proficiency in Python and deep learning frameworks.
• Hands-on experience with LLM APIs like OpenAI and Anthropic.

Responsabilidades

• Design and develop LLM-powered applications using various APIs.
• Implement multi-API workflows and manage data pipelines.
• Fine-tune LLMs on custom datasets for enhanced performance.

Conocimientos

Software engineering

AI and Machine Learning

Python

Deep learning frameworks (PyTorch)

LLM APIs (OpenAI, Anthropic, etc.)

RAG pipeline

MLOps principles

Herramientas

MongoDB

GitHub Actions

Descripción del empleo

Overview

We\'re building the future of AI and computer vision technologies. As an expert in Large Language Models (LLMs), you\'ll play a key role in developing and integrating advanced language model capabilities across our ecosystem.

Responsibilities

• Design, develop, and scale robust LLM-powered applications using various APIs, including OpenAI, Anthropic, and Gemini.
• Implement and manage multi-API workflows using tools like LiteLLM to ensure flexibility and resilience.
• Build sophisticated Retrieval-Augmented Generation (RAG) systems, leveraging advanced techniques like embeddings with Voyage AI, rerankers, and query enrichment.
• Create efficient data pipelines and vector storage solutions using MongoDB Atlas Vector Search.
• Fine-tune LLMs on custom datasets to enhance performance for specialized tasks related to our documentation and user support.
• Collaborate with our YOLO development team to explore and build innovative multi-modal solutions.
• Automate deployment and testing processes using CI / CD pipelines with GitHub Actions.

Requirements

• 5+ years of experience in software engineering, with a strong focus on AI and Machine Learning (ML).
• Expert-level proficiency in Python and deep learning frameworks, particularly PyTorch.
• Proven experience building and deploying applications with LLM APIs such as OpenAI, Anthropic, Gemini, and DeepSeek.
• Hands-on experience with the full RAG pipeline, including vector embeddings, rerankers, and data indexing in databases like MongoDB.
• Practical knowledge of LLM fine-tuning, prompt engineering, and performance optimization.
• Familiarity with MLOps principles and tools, including CI / CD with GitHub Actions.
• A strong interest in computer vision and an understanding of object detection models like Ultralytics YOLO11 is a significant plus.
• Excellent problem-solving skills and the ability to perform in a fast-paced, high-intensity environment.

Benefits

We offer a competitive salary, startup equity, hybrid flexibility, generous time off, flexible hours, top-notch tech, gear, and a supportive team environment.