Location Remote / Hybrid · Greater Toronto Area

We are looking for a Software Intern to help us adapt open-weight large language models to security and identity work. You will take a model from raw data to a measured result: preparing datasets, running fine-tuning jobs, and building the evaluations that tell us whether a change helped.

This is a Fall/Winter internship: hands-on work with real models and real GPUs, alongside the founding team. If you have already fine-tuned a model and want to do it on problems that matter, this is the role for you.

Responsibilities

What you’ll own.

Data & training
Collect, clean, and prepare training and evaluation datasets.
Fine-tune open-weight LLMs with SFT and parameter-effective methods (LoRA / QLoRA).
Run and monitor training jobs on GPUs, and make the most of limited compute.

Evaluation
Build evaluation sets and benchmarks that reflect the tasks we care about.
Compare models and training runs,



and report clearly what worked and what did not.

Required Skills

What you’ll bring day one.

Core
PyTorch and the Hugging Face ecosystem (Transformers, Datasets, PEFT).
Hands-on experience with open-weight LLMs.
Dataset preparation for training and evaluation.
GPU fundamentals: memory, batch sizes, mixed precision.

Nice to Have
Domain-adaptive or continued pretraining (DAPT).
Synthetic data generation.
CUDA.
Docker.
vLLM for serving and quick inference.
Experiment tracking (Weights & Biases, MLflow or similar).
Evaluation frameworks and harnesses.
Reinforcement learning for LLMs.

Why Join Us
Train and evaluate real models, not a sandbox project.
Work directly with the founding team.
Learn how AI meets security and cryptographic identity.
J-18808-Ljbffr

📌 Software Intern Toronto
🏢 Arkion Identity Systems
📍 Toronto