Machine Learning Engineer
Machine Learning Engineer
Spearbit
Spearbit, founded by former Ethereum Foundation engineers, is seeking a Machine Learning Engineer to enhance their Cantina platform, which connects security researchers with projects needing expertise in Web3 security. The role involves leveraging advanced Large Language Models (LLMs) to improve code security and collaboration.
Qualification
- Experience with Python and building ML systems in production.
- Practical experience fine-tuning LLMs (LoRA, QLoRA, DPO/RLHF).
- Familiarity with agentic/autonomous-AI frameworks (LangGraph).
- Solid grounding in software-2-software architectures: REST contracts, event-driven workflows.
- Comfort learning/reading Solidity and reasoning about smart-contract security primitives.
Responsibility
- Design, prototype, and productionise multi-agent pipelines for scanning Solidity smart-contract repositories.
- Build and fine-tune bespoke LLMs and smaller custom models for code understanding.
- Encode and maintain agentic knowledge for autonomous improvement of agents.
- Implement concept-drift and data-drift monitors for model retraining.
- Expose capabilities through FastAPI micro-services and deploy on AWS.
- Collaborate with security researchers to develop detection heuristics from novel attack patterns.
- Deploy and manage machine learning models and services on AWS.
- Collaborate with product managers, data scientists, and engineers to integrate AI solutions.
