AI/LLM Engineer Needed for Fine-Tuning Open Models

We are looking for an experienced LLM Engineer / AI Research Engineer to help us fine-tune open-source models for academic tutoring use cases.
This is a high-impact role with potential long-term collaboration.
Scope of Work
You will help us:
Fine-tune open models (7B–13B range)
Implement LoRA / QLoRA / PEFT training
Prepare instruction-based academic datasets
Optimize models for:
Curriculum-based Q&A
Math reasoning
Coding assistance
Build evaluation pipelines
Package models for deployment (Dockerized inference)
Models Involved
We are working with:
Gemma (Edge deployment model)
LLaMA (Core reasoning model)
DeepSeek (Math / Coding optimization)
Experience with at least one is mandatory. Experience with multiple is a strong plus.
Technical Stack
PyTorch
HuggingFace Transformers
PEFT / LoRA
QLoRA (4-bit training)
MLflow (or similar experiment tracking)
Docker
Kubernetes (nice to have)
Vector DB (Qdrant / Weavi...