AI/LLM Engineer – Model Fine-Tuning, Conversational AI

This is a fully remote position, open to applicants in Poland.

📋 Description

• Train, fine-tune, and enhance existing open-weight language models to elevate conversational performance.

• Develop and sustain model post-training workflows utilizing supervised fine-tuning and parameter-efficient training techniques.

• Prepare, clean, structure, and optimize training datasets.

• Design and implement evaluation frameworks to assess model quality and pinpoint areas for improvement.

• Enhance conversational memory, contextual understanding, and personality consistency across prolonged interactions.

• Develop and refine multilingual conversational capabilities.

• Improve interactions involving multiple AI characters and intricate dialogue scenarios.

• Investigate model failures, inconsistent responses, and behavioral issues.

• Optimize training data, prompting strategies, and response filtering mechanisms based on evaluation insights.

• Conduct GPU-based model training experiments and troubleshoot performance, memory, and training stability challenges.

• Utilize SFT, LoRA, and QLoRA, with exposure to DPO or GRPO.

• Analyze experimental results and identify quantifiable enhancements in model behavior and conversational quality.

• Deploy enhanced models into production environments and monitor their performance.

• Continuously refine deployed models using evaluation data, user interaction patterns, and performance insights.

• Collaborate with AI engineers, product teams, web developers, and DevOps specialists on model integration and deployment.

• Research and assess advancements in open-weight language models and post-training methodologies.

⛳️ Requirements

• Proven hands-on experience in fine-tuning open-weight LLMs and deploying enhanced models into production.

• Strong professional programming skills in Python.

• Practical experience with PyTorch and Hugging Face or similar machine learning frameworks.

• Hands-on experience with supervised fine-tuning (SFT) and parameter-efficient fine-tuning techniques like LoRA and QLoRA.

• Familiarity with preference optimization techniques, particularly DPO or GRPO.

• Experience independently preparing training datasets and constructing model evaluation frameworks.

• Practical experience conducting GPU-based training experiments, including debugging training challenges.

• Strong understanding of model behavior, conversational quality, and post-training optimization.

• Ability to investigate model weaknesses, implement enhancements, and demonstrate measurable outcomes.

• Experience taking model improvements from experimentation to production deployment.

• Previous experience working with consumer-facing AI applications or products.

• Ability to work with complex conversational datasets and systematically assess model outputs.

• Strong analytical thinking, technical problem-solving skills, and attention to detail.

• Ability to collaborate effectively with engineering, product, and infrastructure teams.

• Comfortable taking ownership of model training, evaluation, and deployment tasks.

• Ability to work independently in a fast-paced, international remote environment.

• Based in Europe and willing to operate under a B2B contractor agreement.

• Preferred: experience fine-tuning models for conversational AI, AI companionship, roleplay, or interactive entertainment.

• Preferred: experience enhancing long-context dialogue, memory retention, or personality consistency.

• Preferred: practical experience with multilingual LLM training and evaluation.

• Preferred: experience implementing preference-based optimization using DPO or GRPO.

• Preferred: familiarity with production model monitoring and iterative improvement workflows.

• Preferred: experience optimizing GPU training efficiency and troubleshooting model training infrastructure.

• Preferred: experience with consumer generative AI products serving large user bases.

🏝️ Benefits

• Fully remote working arrangement within Europe.

• Long-term collaboration under a B2B contractor agreement.

• 20 working days of paid leave.

• $100 monthly health insurance allowance.

• Equipment budget to support your remote working setup.

• Access to AI development tools.

• Learning and professional development support.

• Annual team gathering.

• Opportunity to work directly with self-hosted LLMs powering consumer-facing conversational AI products.

• Hands-on ownership of model training, evaluation, and production improvements.

• International working environment within a rapidly growing AI technology company.

• Chance to contribute to innovative advancements in conversational AI and LLM post-training.