Role OverviewJoin a small, fast-moving engineering team in New York City to build a consumer AI assistant focused on sustainability, privacy, and accessible artificial intelligence. The company is already profitable and is planning a significant fundraising round.
What You Will Do
Develop and improve the company's core AI agent harness, including tool calling, memory, system prompts, retrieval, and evaluations. Own features across the consumer chat application and backend, and contribute to the deployment and optimization of NVIDIA B300 GPU infrastructure.
Why It Might Be a Fit
This is an opportunity to join a four-person engineering team, work directly with the founders, and take meaningful ownership of core AI systems and consumer-facing products.
Requirements
- Approximately 1–5 years of engineering experience
- Strong backend or full-stack engineering capabilities
- Hands-on experience building an agent harness or agentic system
- Understanding of agent architecture beyond simply integrating an LLM SDK or API
- Practical experience working with open-source LLMs
- Independent product development experience
- Strong communication skills and ability to collaborate directly with founders and other engineers
- High initiative, independent problem-solving ability, and comfort operating with limited structure
Benefits
- Competitive base compensation
- Substantial equity alongside base compensation
]]>