Lead the design and deployment of cutting-edge AI agents powered by Large Language Models (LLMs) in a fully remote contract role. Drive innovation in autonomous systems, tool integration, and scalable AI solutions for transformative applications.

We are excited to bring on a Senior AI / LLM Agent Engineer to spearhead the development of intelligent, autonomous AI agents at Nan AI Technologies. This remote contract position is perfect for a seasoned engineer passionate about pushing the boundaries of LLM capabilities to create production-ready agent systems that automate complex tasks, enhance decision-making, and deliver seamless user experiences.

Key Responsibilities

• Architect and implement advanced AI agents using state-of-the-art LLMs (e.g., GPT-4, Llama 3, Claude)
• Design scalable agent architectures incorporating reasoning, planning, memory, and external tool integration
• Optimize agent performance through techniques like prompt engineering, fine-tuning, RAG, and evaluation frameworks (e.g., LangSmith)
• Collaborate with cross-functional teams to integrate agents into web, mobile, and enterprise applications
• Conduct experiments, A/B testing, and benchmarking to ensure reliability, efficiency, and safety
• Stay ahead of AI research trends and contribute to open-source projects or internal knowledge sharing

Why Join Us?

Nan AI Technologies is at the forefront of AI innovation, with a mission to empower businesses through intelligent automation. As a remote contractor, you'll enjoy the freedom to work from anywhere while contributing to high-impact projects in Madrid, Spain's vibrant tech ecosystem. This role offers immediate challenges and long-term growth in one of the most exciting fields today.

• 5+ years of experience in AI/ML engineering, with a strong focus on LLMs and AI agent frameworks (e.g., LangChain, LlamaIndex, AutoGen)
• Proficiency in Python and relevant libraries (e.g., Transformers, PyTorch, LangGraph)
• Hands-on experience building agentic workflows, including RAG, tool calling, memory management, and multi-agent systems
• Familiarity with vector databases (e.g., Pinecone, Weaviate, FAISS) and deployment platforms (e.g., Docker, Kubernetes, cloud services like AWS/GCP)
• Strong problem-solving skills and ability to optimize LLM performance for production environments
• Excellent communication skills and experience collaborating in agile, remote teams
• Bachelor's or Master's in Computer Science, AI, or related field

• Competitive monthly salary range tailored to experience
• 100% remote work with flexible hours and autonomy
• Opportunities for professional growth in cutting-edge AI technologies
• Paid time off and contract extensions based on performance
• Access to premium tools, courses, and conferences
• Collaborative, innovative team environment