
LLM Fine-Tuning and Alignment Engineer
Posted 5 days ago

Posted 5 days ago
This is a fully remote position, open to applicants in Colombia, +5 more countries.
β’ Create content for Jala University's Master's program in AI Systems Engineering
β’ Develop a tuned model along with an audit report that encompasses SFT, PEFT/LoRA, DPO/KTO, verifier-driven RL, domain-data preparation, preference optimization, and alignment-auditing methodology
β’ Design module content, labs, an evaluation rubric, and an instructor's guide
β’ Personally develop the deliverable to meet production standards
β’ Guarantee reproducibility through pinned dependencies, containerization, seeded runs, and well-documented decoding parameters
β’ Over 5 years of experience in delivering production software
β’ More than 2 years of experience in production AI/ML
β’ Expertise in production SFT, PEFT, and preference optimization using real domain data
β’ Proven track record in alignment auditing
β’ Comfortable working at a multi-GPU scale and maintaining discipline regarding run lineage
β’ Capability to personally build the artifact to production standards
β’ Public writing samples demonstrating technical explanations, including documentation, workshop materials, a book chapter, or contributions to an open-source project known for its documentation
β’ Proficiency in writing to publication standards
β’ Discipline in ensuring reproducibility, including pinned dependencies, containerization, seeded runs, and documented decoding parameters
β’ Professional proficiency in written English
β’ Familiarity with Axolotl, Unsloth, PEFT, TRL, Hugging Face Inference Endpoints, Modal (H100 / A100 80GB), Weights & Biases, and OpenRouter
β’ Remote work option (home office)
β’ Opportunity to join a dynamic and expanding organization with a global presence
Verdantas
Mercor
Kardex
Leidos
Get handpicked remote jobs straight to your inbox weekly.