LLM Post-Training Engineer

EverAI

Remote regions

Global

Benefits

4w PTO

Similar Jobs

See all

Key Responsibilities:

  • 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, deciding whether the answer is better data, post-training, prompting or classifiers
  • Build training data and evals that directly shape what gets trained next and improve model behavior across personalization, consistency, tone, multilingual and group interactions

Your Qualifications:

  • You've personally post-trained open-weight LLMs for a user-facing product and shipped them to production
  • Strong Python, PyTorch and Hugging Face, with hands-on GPU training and debugging
  • You build data and evals yourself and make decisions from evidence

Why EverAI?:

  • Exponential Growth: From 60M users in 3 years, to 100M next and 500M beyond
  • Track Record of Category-Creating Innovation: We consistently launch world-first AI applications
  • Global Impact: Top-tier user growth, real-world adoption, and cultural relevance

EverAI

EverAI is building the world's largest AI companionship platform, redefining relationships for millions with its proprietary moderation system EverGuard. The company has a team of about 100 enthusiastic, passionate, and hardworking people with strong entrepreneurial experience.

Apply for This Position