Junior AI Engineer - Site: Rome

Aieng; Roma; Híbrido; EUR 28.000 - 48.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Mentoring

Hands-on growth in RAG

Hybrid workplace

Descripción de la vacante

Aieng is seeking a Junior AI Engineer to join our engineering team in Rome, working on AI-driven features for our platform. You will collaborate with senior engineers to build RAG pipelines, agentic workflows, and local LLM inference, writing Python services that integrate with a C#/.NET backend.

You will develop Python AI services, expose REST APIs, and contribute to deploying and testing open-weight models. The role emphasizes hands-on learning in a hybrid work environment.

Formación

• Proficient in Python and basic software engineering practices (Git, testing, REST APIs).
• Hands-on experience building RAG pipelines and agentic workflows with LLMs.
• Knowledge of multi-agent architectures and coordinating agents.
• Interest in integrating Python AI services with a C#/.NET backend; basic C# knowledge is a plus.
• Solid fundamentals in ML and NLP.
• Degree in CS/AI/Engineering or related field; 0–2 years experience.

Responsabilidades

• Build and improve RAG pipelines: document ingestion, embeddings, and retrieval from vector databases.
• Develop reasoning agents and multi-agent workflows, evaluate reliability.
• Help deploy and test open-weight models for local inference.
• Build Python AI services and expose REST APIs that integrate with our C#/.NET platform, in collaboration with the backend team.

Conocimientos

Python

Git

REST APIs

Testing

ML basics

NLP basics

LLMs / RAG pipelines

C# / .NET basics

Teamwork

Educación

Bachelor's or equivalent in CS/AI/Engineering

Herramientas

Ollama

vLLM

llama.cpp

Qdrant

Milvus

Weaviate

Descripción del empleo

About Aieng

Aieng is a high-growth innovative startup focused on delivering next-generation engineering solutions. We bridge the gap between ambitious vision and technical reality by investing heavily in research, development, and top-tier talent. We are building an intelligent automation platform based on modern microservices, where AI is an active participant in engineering and design processes.

Your Role

As a Junior AI Engineer, you will join our engineering team to help build AI-driven features for our platform, working on RAG pipelines, agentic and multi-agent workflows, and local LLM inference. With guidance from senior engineers, you will write Python services that integrate with our core C#/.NET backend.

What You'll Do

• Build and improve RAG pipelines: document ingestion, embeddings, and retrieval from vector databases.
• Develop reasoning agents and multi-agent workflows, and evaluate their reliability.
• Help deploy and test open-weight models for local inference.
• Build Python AI services and expose them through clean REST APIs that integrate with our C#/.NET platform, in collaboration with the backend team.

Requirements

• Good proficiency in Python and basic software engineering practices (Git, testing, REST APIs).
• Hands-on experience (even academic or personal) building RAG pipelines and agentic workflows with LLMs.
• Practical knowledge of multi-agent architectures (e.g., orchestrating multiple specialized agents).
• Interest in integrating Python AI services with a C#/.NET backend; basic C# knowledge is a strong plus.
• Solid fundamentals in Machine Learning and NLP.
• Degree (or final year) in Computer Science, AI, Mathematics, Engineering, or a related field.
• 0–2 years of experience, including internships or thesis work. Please share a link to your projects!

Nice to Have

• Experience with local inference tools (e.g., Ollama, vLLM, llama.cpp).
• Vector databases (e.g., Qdrant, Milvus, Weaviate).
• Fine-tuning (e.g., LoRA), for example for domain-specific engineering drawing pipelines.
• Computer Vision or OCR experience.

Soft Skills

• Engineering Mindset: Strong analytical, problem-solving, and communication skills, with a focus on delivering working, reliable features.
• Teamwork: Ability to work collaboratively in a hybrid environment, both in-person and remotely.
• Curiosity and willingness to learn fast in a rapidly evolving field.

What We Offer

• Mentoring from senior engineers and real ownership on industrial AI projects.
• Hands-on growth in RAG, agentic systems, and local LLM inference.

Workplace

• Hybrid Workplace. Main Site: Rome.