Senior LLM Fine-Tuning Engineer (Remote)

Bright Vision Technologies; Oregon; Hybrid; USD 100,000 - 150,000; Full time

Job summary

Bright Vision Technologies is seeking a Large Language Model Specialist for 100% remote work in the U.S. The role focuses on designing, executing, and operationalizing fine-tuning workflows for LLMs across supervised, preference-based, and reinforcement learning approaches.

Expect deep experience with modern training stacks, data curation, rigorous evaluation, and production-grade engineering to ship reliable models.

Qualifications

• Master's or PhD in CS/ML or related field.
• 6+ years of ML research/engineering with LLM exposure.
• Strong Python and PyTorch proficiency.
• Experience fine-tuning transformer models at scale.
• Experience with distributed training (FSDP, ZeRO, pipeline parallelism).
• Experience with RLHF or DPO.
• Strong evaluation design and benchmarks knowledge.
• Experience operating GPU-cluster training and recovering from failures.
• Excellent written and verbal communication skills.
• Track record of shipping LLM work.

Responsibilities

• Design and execute fine-tuning experiments for LLMs (supervised, DPO, RLHF).
• Lead dataset construction, curation, and QA for instruction tuning and preferences.
• Build scalable training pipelines on modern distributed frameworks.
• Tune hyperparameters and training stability strategies for large models.
• Implement parameter-efficient fine-tuning methods (LoRA, QLoRA, adapters).
• Design rigorous evaluation suites including benchmarks and human evals.
• Implement safety and policy evaluations across releases.
• Operate large-scale training jobs on GPU clusters and recover from failures.
• Improve throughput with mixed precision and efficient attention.
• Manage model artifacts and reproducibility across experiments.
• Collaborate with product/research/platform teams on roadmaps.
• Document training methodology and results for varied audiences.
• Mentor engineers on fine-tuning best practices and responsible deployment.
• Keep current with LLM research and translate advances into production recipes.

Skills

Python

PyTorch

LLM fine-tuning

Distributed training

Evaluation design

Communication skills

Mentorship

Education

Master's or PhD in CS/ML or related field

6+ years ML research/engineering

Tools

FSDP

ZeRO

Pipeline parallelism

RLHF

DPO

Job description

Bright Vision Technologies is seeking a Large Language Model Specialist for 100% remote work in the U.S. The role focuses on designing, executing, and operationalizing fine-tuning workflows for LLMs across supervised, preference-based, and reinforcement learning approaches.

Expect deep experience with modern training stacks, data curation, rigorous evaluation, and production-grade engineering to ship reliable models.