Lead AI Engineer

Spendbase is expanding its product portfolio and launching LLM.API — a standalone open-source AI infrastructure product developed by the Spendbase engineering team.

LLM.API provides a unified API for working with multiple large language model providers and is designed for companies running AI features in production. The platform is built primarily in JavaScript and is developed as an open-source project.

We are looking for a Lead AI Engineer to join Spendbase and take technical ownership of LLM.API. This role is responsible for defining how the AI layer of the product is designed, built, and operated, from early architecture decisions to production scalability.

You will work closely with CEO, CTO and product team and will be accountable for the reliability, performance, and cost efficiency of AI functionality in real-world use cases.

What you’ll do:

• Own the architecture and implementation of the AI / LLM layer of LLM.API
• Design how requests are handled and executed across multiple LLM providers
• Make decisions on model usage based on reliability, latency, quality, and cost
• Ensure stable and predictable behavior of AI features in production
• Define and implement monitoring, limits, and cost control for AI usage
• Work closely with the CEO, CTO and Product team on technical direction and roadmap
• Take responsibility for AI-related production issues and improvements
• Contribute hands-on at early stages and later help grow and guide the engineering team

What we’re looking for:

• 6+ years of professional software engineering experience
• 2+ years of hands-on experience working with AI / LLMs in production
• Previous experience as Senior Engineer, Tech Lead, Staff Engineer, or similar
• Experience owning and launching production systems or platforms
• Strong backend or platform engineering background
• Solid experience with JavaScript / Node.js in production environments
• Experience building and maintaining API-first, scalable systems
• Hands-on experience integrating LLM providers (OpenAI, Anthropic, open-source models, etc.)
• Good understanding of trade-offs between model quality, latency, reliability, and cost
• Experience operating systems that depend on third-party services
• Ability to make architectural decisions with incomplete or evolving requirements
• Experience working closely with product and business stakeholders
• Experience mentoring engineers or taking technical ownership within a team

What we offer:

• Competitive compensation and regular performance reviews
• Paid vacation, sick leave, and overtime compensation
• Online medical consultations
• Career growth opportunities through ownership and leadership
• Opportunity to work on a standalone, open-source AI product
• Remote-first culture with flexible working hours

Join the growth!