About the job
About the Role
Join Onyx, an esteemed open-source project that has captivated hundreds of thousands of users. With over 10,000 stars and a vibrant community of over 3,000 members on platforms like Slack and Discord, your contributions could impact millions in the future.
Your Impact
As a Machine Learning Engineer at Onyx, you will play a pivotal role in enhancing our knowledge layer on top of Large Language Models (LLMs). You will tackle complex challenges such as multi-hop question answering, needle-in-haystack retrieval, and advanced Retrieval-Augmented Generation (RAG) techniques.
Key Responsibilities
- Design and implement knowledge graphs based on LLMs, exploring advanced RAG methods and cutting-edge information retrieval algorithms.
- Enhance user experience through innovative features like feedback learning, personalized search, and Subject Matter Expert (SME) suggestions.
- Develop a semantic understanding of organizational priorities to improve Onyx's answering capabilities.
- Manage projects from initial conception through validation to production deployment.
- Collaborate closely with our Founders and Head of AI to shape product direction and contribute to our AI/ML strategy.
Success Criteria
- 3+ years of experience in AI/ML engineering, focusing on real-world applications.
- In-depth expertise with PyTorch/TensorFlow, natural language processing (NLP) models, and standard machine learning algorithms.
- Stay current with advancements in open-source and proprietary LLMs, RAG, and agent frameworks.
- Strong software engineering skills, capable of building backend features using web frameworks, ORMs, and relational databases.
- Excellent communication skills, with the ability to collaborate effectively across teams.
⭐ Bonus Skills
- Familiarity with full-stack technologies, including TypeScript, React, Next.js, Python, and PostgreSQL.
- Passion for writing technical blogs to position Onyx as a leader in the field.

