Mid/Senior Ai Llm Engineer

Pubblicato il 18-11-2026 · Jobgether · Italia

pbThis position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Mid/Senior AI LLM Engineer based in Italy. /b /ppAs a Mid/Senior AI LLM Engineer, you will develop, fine-tune, and optimize self-hosted large language models that power personalized, engaging AI conversations. You will work across the full model development lifecycle, from preparing training datasets and running GPU-based experiments to evaluating performance and deploying improvements into production. Your work will help enhance conversational quality, long-term memory, personality consistency, and multilingual interactions. Collaborating with AI engineers, product specialists, web developers, and DevOps teams, you will turn experimental findings into reliable, scalable solutions. This hands-on role offers the opportunity to work with open-weight models, advanced fine-tuning techniques, and practical AI evaluation frameworks. You will join a remote-first environment focused on building innovative, consumer-facing AI products while continuously improving model performance and user experience. /pbr/h3Accountabilities /h3ullipFine-tune and optimize existing open-weight large language models to improve conversational quality, response accuracy, consistency, and personalization. /p /lilipPrepare, curate, and enhance training datasets to support effective model learning, reduce undesirable outputs, and improve the relevance and naturalness of generated responses. /p /lilipDesign and implement evaluation frameworks, benchmarks, and testing methodologies to measure model quality, identify weaknesses, and validate improvements. /p /lilipImprove conversational memory, personality consistency, and the ability of models to maintain coherent, context-aware interactions over extended conversations.



/p /lilipDevelop multilingual conversational capabilities and support interactions involving multiple characters, ensuring natural and consistent behavior across different scenarios. /p /lilipInvestigate model failures and performance limitations, adjusting training data, prompts, model configurations, and response filters to address identified issues. /p /lilipConduct GPU-based training and fine-tuning experiments, troubleshoot infrastructure and performance issues, and optimize training workflows for efficiency and reliability. /p /lilipApply modern model adaptation and alignment techniques, including supervised fine-tuning, LoRA, QLoRA, and preference-based optimization methods where appropriate. /p /lilipDeploy improved models into production environments, monitor their performance, analyze user-facing outcomes, and implement iterative refinements based on evaluation results. /p /lilipCollaborate with AI engineering, product, web development, and DevOps teams to integrate model improvements into consumer-facing applications and align technical work with product objectives. /p /lilipWork with sensitive conversational use cases and moderation requirements, balancing model behavior, user experience, and applicable content policies. /p /li /ulh3Requirements:



/h3ullipProven hands-on experience fine-tuning open-weight large language models and deploying models into production environments. /p /lilipStrong Python programming skills, including experience developing, testing, and maintaining machine-learning workflows. /p /lilipPractical experience with PyTorch and Hugging Face or comparable machine-learning frameworks and model development tools. /p /lilipExperience with model training and adaptation techniques such as supervised fine-tuning (SFT), Low-Rank Adaptation (LoRA), and Quantized Low-Rank Adaptation (QLoRA). /p /lilipFamiliarity with preference-based training and alignment techniques, such as Direct Preference Optimization (DPO) or Group Relative Policy Optimization (GRPO). /p /lilipExperience preparing and managing training datasets, improving data quality, and developing evaluation frameworks to assess model behavior and output quality. /p /lilipPractical experience with GPU-based model training, performance optimization, and debugging training-related technical issues. /p /lilipStrong analytical and problem-solving skills, with the ability to investigate model behavior, identify root causes, design experiments, and demonstrate measurable improvements. /p /lilipUnderstanding of the challenges involved in deploying and maintaining LLM-powered applications, including response quality, consistency, inference performance, and ongoing monitoring. /p /lilipExperience working on consumer-facing AI products, with an understanding of how model quality and conversational behavior affect user experience. /p /lilipComfort working with minimally restricted or uncensored AI models, including explicit adult or NSFW content and sensitive moderation material, while applying appropriate safeguards and content-handling practices. /p /lilipAbility to work independently in a remote environment, manag
Max. 8 MB. Formati Accettati: PDF, RTF, DOC, DOCX, ODT.