Publié il y a 17 jours
Software Intern
@ Arkion-tech
Toronto, Ontario
SIGNAUX
En bref
Arkion-tech is hiring a Software Intern for a Fall/Winter internship to adapt open-weight large language models to security and identity work. The work covers dataset preparation, fine-tuning jobs on GPUs, and building evaluations to measure results. The role is hands-on and works directly alongside the founding team.
Responsabilités :
- Collect, clean and prepare training and evaluation datasets
- Fine-tune open-weight LLMs with SFT, LoRA and QLoRA
- Run and monitor GPU training jobs
- Build evaluation sets and benchmarks
- Compare models and report results
Résumé des exigences :
- PyTorch and Hugging Face ecosystem experience
- Hands-on experience with open-weight LLMs
- Fine-tuning with SFT, LoRA or QLoRA
- Dataset preparation and model evaluation
- GPU fundamentals: memory, batch sizes, mixed precision
Outils et compétences
PyTorchHugging Face TransformersHugging Face DatasetsHugging Face PEFTGPUCUDADockervLLMWeights & BiasesMLflow
Source et dates
Type de source non vérifié · apify-linkedin
- Date publiée par l’employeur
- 2026-10-27
- Première détection par notre source
- 2026-11-14
- Mise à jour du dossier source
- 2026-11-14
Ces dates décrivent le dossier source, pas une vérification en direct du recrutement. Consultez l’offre originale.
Détails du poste
| Niveau | Débutant |
| Domaine | Développement logiciel |
| Saisonnier | Oui |
| Milieu de travail | Bureau |
| Position | Surtout assis |
| Exigences physiques | physique faible · ordinateur élevé |
Résumé et détails rédigés par l’IA à partir de l’offre; l’offre de l’employeur fait foi.
Arkion-tech
Description
About The Role
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
What you’ll bring day one.
Core
01
Train and evaluate real models, not a sandbox project.
02
Work directly with the founding team.
03
Learn how AI meets security and cryptographic identity.
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-efficient methods (LoRA / QLoRA).
- Run and monitor training jobs on GPUs, and make the most of limited compute.
- 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.
What you’ll bring day one.
Core
- PyTorch and the Hugging Face ecosystem (Transformers, Datasets, PEFT).
- Hands-on experience with open-weight LLMs.
- Fine-tuning: SFT, LoRA / QLoRA.
- Dataset preparation for training and evaluation.
- Model evaluation.
- GPU fundamentals: memory, batch sizes, mixed precision.
- Domain-adaptive or continued pretraining (DAPT).
- Synthetic data generation.
- CUDA.
- Docker.
- vLLM for serving and fast inference.
- Experiment tracking (Weights & Biases, MLflow or similar).
- Evaluation frameworks and harnesses.
- Reinforcement learning for LLMs.
01
Train and evaluate real models, not a sandbox project.
02
Work directly with the founding team.
03
Learn how AI meets security and cryptographic identity.
Journal
Visible seulement par vous. Conservé sur cet appareil, et dans votre compte une fois connecté.