LLM Engineer - Post-Training (Remote - Europe)

The role

You will fine-tune open-weight LLMs and improve model behavior for a large AI companionship platform. You will work across data, post-training, evals, and model behavior to ship improvements to production.

What you will do

• Fine-tune open-weight LLMs using SFT, LoRA/QLoRA and post-training methods such as DPO and GRPO
• Diagnose model failures and turn them into experiments
• Build training data and evals that directly shape what gets trained next
• Improve model behavior across personalization, consistency, tone, multilingual and group interactions
• Ship to production and use real user behavior to guide the next iteration
• Speed up the training loop so experiments are faster, easier to compare, and more reproducible

Required qualifications

• Personally post-trained open-weight LLMs for a user-facing product and shipped them to production
• Worked where AI was core to the product or business
• Fine-tuning is core to your experience
• Strong Python, PyTorch and Hugging Face, with hands-on GPU training and debugging
• Build data and evals yourself and make decisions from evidence
• Can take work beyond notebooks into production
• Use AI tools daily in your own engineering work
• Fully comfortable working with uncensored models and explicit NSFW content, including harmful material when developing and evaluating moderation system

Nice to have

• Experience with conversational AI, roleplay products, or highly personalized consumer AI
• Multilingual LLMs
• Moderation, safety, or adversarial testing
• Multimodal models
• Open-source LLM / post-training contributions

Benefits

• 4 weeks (20 working days) of PTO per year
• Annual in-person meetup
• Monthly allowance of 100 USD for health insurance expenses
• Access to unlimited 1:1 sessions with psychologists and lifestyle experts through OpenUp for you and up to three family members
• Co-working space budget up to twice per month (35 EUR / 40 USD per visit)
• Dedicated funds for professional growth: courses, books, conferences, events, or certifications
• Laptop provided
• Monitor budget up to 250 USD
• Keyboard/mouse/mic/headphones budget up to 150 USD
• Premium access to ChatGPT, Hugging Face, Claude Code, and other tools

About the company

EverAI is building the future of AI companionship with 50 million users. The company is a remote team of approximately 100 people led by an entrepreneurial founding team.