Fine-Tuning Engineer
You will adapt open-source language models to specialized client domains through instruction tuning, dataset preparation, and parameter optimization.
What you'll work with.
As a Fine-Tuning Engineer at TheWebVale, you will specialize open-weight foundation models to perform specific client business tasks. You will adapt models like Llama, Mistral, and Qwen for legal document parsing, clinic terminology triage, and customized educational tutoring. You will partner with AI research engineers and backend developers throughout our two-to-three week release cadences. You will balance model training loss with inference speed, deploying specialized weights that clients own and run privately.
Your day to day.
6 things, one at a time. Keep scrolling.
Prepare, format, and tokenize instruction datasets for supervised fine-tuning (SFT).
Fine-tune open-weight models using PEFT techniques including LoRA, QLoRA, and full weights.
Monitor training metrics, learning rate schedules, and loss curves to prevent overfitting.
Evaluate fine-tuned models against baseline foundation weights across standard benchmarks.
Quantize and export fine-tuned adapter weights for low-latency serving on local servers.
Document training hyperparameters, compute budgets, and reproducibility steps.
What we look for.
6 things, one at a time. Keep scrolling.
Possess 3–5 years of software or machine learning experience with dedicated fine-tuning work.
Demonstrate deep proficiency with Python, PyTorch, Hugging Face Transformers, and PEFT.
Show practical experience fine-tuning models on GPU cloud instances with CUDA.
Understand tokenization nuances, padding strategies, loss functions, and weight merging.
Possess disciplined habits tracking experiments using tools like Weights & Biases or MLflow.
Communicate model performance gains and hardware trade-offs clearly to team leaders.
What you get.
Three steps, no tricks.
- 1
Intro chat
A short call about what you want to work on and how you like to work.
- 2
Work review
Walk us through projects, code or designs you are proud of.
- 3
Paid task
A small paid task or pairing session, so both sides see the fit.
Apply for Fine-Tuning Engineer .
Tell us about your work. We reply to every application, usually within a few days.