LLM Fine-Tuning Engineer – Conversational AI Specialist

Salve.Inno Consulting; Województwo pomorskie; A distancia; PLN 393.000 - 612.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Fully remote within Europe

Long-term B2B collaboration

20 working days paid leave

$100 monthly health insurance stipend

Equipment budget for remote setup

Access to AI development tools

Professional development support

Annual team gathering

Hands-on ownership of model training/e

production improvements

Descripción de la vacante

Salve.Inno Consulting seeks an experienced AI/LLM Engineer to tune and deploy open-weight models for conversational AI. You will work on training pipelines, data curation, and evaluation, ensuring high-quality multilingual interactions.

The role emphasizes practical model engineering over research, with ownership of end-to-end model improvements. Remote Europe-based contractor role under a B2B arrangement, offering long-term collaboration, 20 paid leave days, health insurance stipend, equipment

Formación

• Hands-on experience fine-tuning open-weight LLMs and deploying to production.
• Experience with Python and ML frameworks (PyTorch/Hugging Face).
• Experience with SFT, LoRA/QLoRA, and preference optimization approaches (DPO/GRPO).
• Ability to prepare training data, build evaluation frameworks and deploy models.

Responsabilidades

• Train and fine-tune open-weight language models to improve conversational performance.
• Develop post-training workflows using supervised fine-tuning and parameter-efficient methods.
• Prepare and clean training datasets to enhance response quality and consistency.
• Build evaluation frameworks to measure model quality and guide improvements.
• Deploy improved models to production and monitor performance.
• Collaborate with AI engineers, product and DevOps for integration and deployment.
• Research and evaluate developments in open-weight LLMs and post-training methods.

Conocimientos

Python programming

PyTorch

Hugging Face

SFT (supervised fine-tuning)

LoRA/QLoRA

DPO/GRPO

GPU training

data preparation

model evaluation

production deployment

Herramientas

CUDA

Git

Descripción del empleo

Salve.Inno Consulting seeks an experienced AI/LLM Engineer to tune and deploy open-weight models for conversational AI. You will work on training pipelines, data curation, and evaluation, ensuring high-quality multilingual interactions.

The role emphasizes practical model engineering over research, with ownership of end-to-end model improvements. Remote Europe-based contractor role under a B2B arrangement, offering long-term collaboration, 20 paid leave days, health insurance stipend, equipment