Fullstack Engineer

Onyx is the open source GenAI platform connected to your company's docs, apps, and people. We ingest and sync from all sources of information (Google Drive, Slack, GitHub, Confluence, Salesforce, etc.) to provide a centralized place for users to ask about anything. Imagine your most knowledgeable co-workers, all-rolled into one, and available 24/7! We believe that every modern team will be adopting knowledge enhanced GenAI within the next 5 years and it is our goal to bring this technology to all the teams of the world. We raised a $10M seed coming out of YCombinator, backed by Khosla Ventures (early/seed backers of OpenAI, Doordash, GitLab, etc.) and First Round Capital (Notion, Square, Roblox, etc.). Our customers include of the best teams in the world like Netflix, Ramp, Applied Intuition and dozens of others. We also have incredible open source users like Roku, Zendesk, L3Harris and more. 💥 Your impact Onyx is a popular open source project with hundreds of thousands of users. The project has over 10K stars and over 3K community members across Slack and Discord (these stats may already be out of date when you read this). You’ll have the opportunity to build in the open and your work may be used by millions of people in the future. 💡 About the role As an early hire, you'll play a pivotal role in shaping the core product. Help us become the biggest “GenAI for work” application in the world. This is an in-person role based in San Francisco, CA. You’ll be: Building a consumer grade UI experience for the GenAI Chat, Enterprise Search, Agents, and Admin features Extending the backend functionalities and APIs (see below) Improving the flexibility and quality of the search pipeline, building a semantic understanding of customer organizations, extending the current permission/access controls, and expanding the knowledge curation features Implementing the latest approaches in NLP research like LLM based Knowledge Graphs, StructRAG, Agent/Deep-Research, etc. to increase the range of questions the system can answer (AI / deep learning experience not required) Own the entire development cycle of new features, from conception to production Collaborate with the founders and team to shape and influence the direction of the product and contribute to the engineering strategy Building a consumer grade UI experience for the GenAI Chat, Enterprise Search, Agents, and Admin features Extending the backend functionalities and APIs (see below) Improving the flexibility and quality of the search pipeline, building a semantic understanding of customer organizations, extending the current permission/access controls, and expanding the knowledge curation features Implementing the latest approaches in NLP research like LLM based Knowledge Graphs, StructRAG, Agent/Deep-Research, etc. to increase the range of questions the system can answer (AI / deep learning experience not required) Own the entire development cycle of new features, from conception to production Collaborate with the founders and team to shape and influence the direction of the product and contribute to the engineering strategy 🚀 You’ll be successful if you… Have 1-5 years (or more) of software engineering experience building real-world applications Know Typescript/React/NextJS, Python, Relational DBs (Postgres) Enjoy working in a fast moving startup with low amounts of process Have excellent communication skills, with a strong ability to collaborate with others (both teammates and external customers) Have 1-5 years (or more) of software engineering experience building real-world applications Know Typescript/React/NextJS, Python, Relational DBs (Postgres) Enjoy working in a fast moving startup with low amounts of process Have excellent communication skills, with a strong ability to collaborate with others (both teammates and external customers) ⭐ Bonus points Experience with Docker/Kubernetes, cloud technologies (AWS, GCP, Azure), and on-prem/cloud deployments Experience (or even just interest) in AI (NLP, Deep Learning, GenAI) and information retrieval Previous founder or early engineer at seed/series-A startup Experience with Docker/Kubernetes, cloud technologies (AWS, GCP, Azure), and on-prem/cloud deployments Experience (or even just interest) in AI (NLP, Deep Learning, GenAI) and information retrieval Previous founder or early engineer at seed/series-A startup Technical Challenges: Information retrieval at scale Access controls, scalability, high availability, data freshness, etc. Building the optimal UX for knowledge enhanced GenAI LLM based knowledge graphs, multi-hop queries, aggregation type query handling Semantic representation of the organization, subject matter experts, and major topics Learn from user feedback Personalized search [Future] Code search, NL-to-SQL, Excel/Sheets calculations Information retrieval at scale Access controls, scalability, high availability, data freshness, etc. Building the optimal UX for knowledge enhanced GenAI LLM based knowledge graphs, multi-hop queries, aggregation type query handling Semantic representation of the organization, subject matter experts, and major topics Learn from user feedback Personalized search [Future] Code search, NL-to-SQL, Excel/Sheets calculations Tech Stack: Typescript/NextJS, Python, Postgres, Redis, Docker/Kubernetes AI Stack: Transformers and deep learning, RAG, knowledge graphs, LLM based agent, search engine/vector database Phone Screen / Overview (30 mins) Practical Coding Interview (30 mins) Work Trial (2-3 days in person, compensated) Phone Screen / Overview (30 mins) Practical Coding Interview (30 mins) Work Trial (2-3 days in person, compensated)