Remote LLM Fine-Tuning & Conversational AI Engineer

Salve.Inno Consulting; Barcelona; Remote; EUR 90,000 - 150,000; Full time

Benefits offered by this job

Fully remote in Europe

B2B contractor arrangement

20 days paid leave

Health insurance allowance $100/mo

Equipment budget

Job summary

Salve.Inno Consulting is seeking an experienced AI/LLM Engineer to lead model fine-tuning and open-weight deployments for conversational AI products. You will own training pipelines, data prep, evaluation, and production rollout, collaborating with AI engineering, product, and DevOps teams across Europe.

The role demands hands-on expertise with Python, PyTorch, SFT, LoRA/QLoRA, and multilingual capabilities, plus a track record of producing real improvements in model behavior and user experience.

Qualifications

• Proven hands-on experience fine-tuning open-weight LLMs and deploying in production.
• Strong Python programming skills.
• Practical experience with PyTorch and Hugging Face or comparable ML frameworks.
• Hands-on experience with supervised fine-tuning (SFT) and parameter-efficient fine-tuning (LoRA/QLoRA).
• Familiarity with preference optimisation techniques (DPO/GRPO).
• Experience preparing training datasets and building evaluation frameworks.
• GPU-based training experiments and debugging training issues.
• Understanding of model behaviour, conversational quality and post-training optimisation.
• Experience taking model improvements from experimentation to production deployment.
• Experience with consumer-facing AI applications or products.
• Ability to work with complex conversational datasets and assess outputs.
• Strong analytical, problem-solving, and collaborative skills.
• Ability to work independently in a fast-paced, international remote environment.
• Based in Europe under a B2B contractor agreement.

Responsibilities

• Train, fine-tune and optimise open-weight language models for conversational performance.
• Develop model post-training workflows using supervised fine-tuning and parameter-efficient methods.
• Prepare and improve training datasets for accuracy and naturalness.
• Design evaluation frameworks to measure model quality and identify improvements.
• Improve multilingual conversational capabilities and memory across interactions.
• Collaborate with AI engineering, product, web development and DevOps teams.
• Investigate failures and memory/behavioural issues; deploy improvements to production.
• Monitor training stability and performance in GPU environments.
• Apply SFT, LoRA/QLoRA with DPO/GRPO approaches where relevant.
• Research open-weight LLM developments and post-training methodologies.

Skills

Python

PyTorch

Hugging Face

SFT

LoRA

QLoRA

DPO/GRPO

GPU training

Tools

Hugging Face

CUDA

Job description

Salve.Inno Consulting is seeking an experienced AI/LLM Engineer to lead model fine-tuning and open-weight deployments for conversational AI products. You will own training pipelines, data prep, evaluation, and production rollout, collaborating with AI engineering, product, and DevOps teams across Europe.

The role demands hands-on expertise with Python, PyTorch, SFT, LoRA/QLoRA, and multilingual capabilities, plus a track record of producing real improvements in model behavior and user experience.