Remote LLM Fine-Tuning Engineer

Bright Vision Technologies; Plymouth (MN); Remote; USD 100,000 - 150,000; Full time

Job summary

Bright Vision Technologies seeks an LLM Fine-Tuning Engineer to design, execute, and operationalize fine-tuning workflows for large language models across supervised, preference-based, and RLHF approaches. You'll work with product, design, and engineering teams to translate requirements into robust training pipelines, while balancing data quality, compute, evaluation rigor, and shipping velocity.

Remote-first role across the U.S.; strong production engineering discipline is essential.

Qualifications

• Advanced degree or equivalent in CS/ML.
• 6+ years of ML research/engineering with LLM exposure.
• Proficiency in Python and PyTorch.
• Experience fine-tuning transformer models at scale.
• Familiarity with distributed training (FSDP, ZeRO, pipeline parallelism).
• Experience with RLHF, DPO, or similar.
• Strong evaluation design and benchmarks.
• Experience operating GPU clusters.
• Strong written and verbal communication.
• Track record of shipping LLM work.

Responsibilities

• Design and run fine-tuning experiments for LLMs using supervised, RLHF, and related techniques.
• Lead dataset construction and quality assurance for instruction tuning.
• Build scalable training pipelines on modern distributed frameworks.
• Tune hyperparameters and training stability for large models.
• Implement parameter-efficient fine-tuning methods (LoRA, QLoRA, adapters).
• Design rigorous evaluation suites including benchmarks and human evaluation.
• Implement safety and policy evaluations across releases.
• Operate large-scale GPU training jobs and recover runs.
• Optimize throughput with mixed precision and efficient attention.
• Manage model artifacts and reproducibility across experiments.
• Collaborate with product, research, and platform teams on roadmaps.
• Document methodology, results, and decisions for diverse audiences.
• Mentor engineers on fine-tuning best practices and deployment.
• Stay current with LLM research and translate advances to production.

Skills

Python

PyTorch

LLM Fine-tuning

Distributed training

Communication

Model evaluation

Education

Master's or PhD in Computer Science, ML, or related field

Tools

FSDP

ZeRO

Pipeline parallelism

Job description

Bright Vision Technologies seeks an LLM Fine-Tuning Engineer to design, execute, and operationalize fine-tuning workflows for large language models across supervised, preference-based, and RLHF approaches. You'll work with product, design, and engineering teams to translate requirements into robust training pipelines, while balancing data quality, compute, evaluation rigor, and shipping velocity.

Remote-first role across the U.S.; strong production engineering discipline is essential.