Design and implement document intelligence pipelines for contract parsing, data extraction, and document classification
Build and fine-tune LLM-based systems for legal document analysis, clause identification, and obligation extraction
Develop NLP models for entity recognition, relationship extraction, and semantic understanding of legal text
Create and curate training datasets from Australian legal documents (conveyancing contracts, leases, facility agreements)
Integrate AI capabilities into the company's product suite via well-designed, reliable APIs
Design evaluation frameworks to benchmark model performance against legal expert baselines
Collaborate with conveyancing and legal domain experts to validate AI outputs for accuracy and trustworthiness
Stay current with advances in document AI, transformer architectures, retrieval-augmented generation, and fine-tuning

3+ years of experience in machine learning, NLP, or AI engineering with production deployment experience
Strong proficiency in Python and ML frameworks (PyTorch, TensorFlow, or Hugging Face Transformers)
Experience building production ML systems including model training, evaluation, deployment, and monitoring
Hands-on experience with LLMs — prompt engineering, fine-tuning, RAG architectures, and evaluation
Understanding of document processing, OCR, and information extraction techniques
Experience with cloud ML infrastructure (AWS SageMaker, or equivalent)
Strong software engineering fundamentals — clean code, testing, version control, CI/CD
Based in or willing to relocate to Sydney or Melbourne, Australia

Lead Engineer – Full Stack Developer, Legal Automation, AI

Key skills