AI Software Development Engineer
Pubblicato il 27-10-2026 - Aieng in Roma
pAieng 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. /ph3Your Role /h3pAs an AI Engineer, your mission is to develop and implement AI-driven solutions, focusing on local inference systems, agentic workflows, and the practical application of Large Language Models. You will actively participate in software development to integrate these intelligent features into our platform, ensuring that AI tools interface seamlessly with our core .
NET backend architecture. /ph3Key Responsibilities /h3ulliAI Deployment Inference: Deploy and run open-weight models efficiently, ensuring they integrate securely and reliably into our core platform. /Develop reasoning agents and Retrieval-Augmented Generation (RAG) pipelines, managing document ingestion and interacting with Vector Databases for contextual retrieval. /liliModel Fine-Tuning: Help adapt and fine-tune existing foundational models to our specific industrial and engineering domains. /liliCross-Functional Collaboration:
Collaborate with the engineering team to build AI services in Python that integrate cleanly with our core C# platform. /li /ulh3Technical Skills (Hard Skills) /h3ulliSoftware Development: Solid proficiency in Python. Practical familiarity with C#/.
NET is a strong plus for cross-ecosystem integration. /liliApplied AI NLP: Practical experience with Large Language Models, Natural Language Processing (NLP), and moving AI concepts from theory to working applications. /Hands-on experience managing modern local inference ecosystems (e.g., vLLM, Ollama) and integrating them with Vector Databases (e.g., liliMachine Learning Computer Vision (Preferred): Experience with traditional Machine Learning pipelines and Computer Vision techniques is highly preferred to support future multimodal capabilities. /Ability to build and expose robust RESTful APIs for AI features, ensuring predictable data flows. /Ability to work collaboratively in a hybrid environment, both in-person and remotely. /2+ years of proven software engineering experience with a strong, demonstrable focus on building and deploying Applied AI, LLMs, or inference pipelines. /A degree in Computer Science, AI, or a related field is required; advanced degrees are a plus. /li /ul #J-18808-Ljbffr