Concentrate AI · 1 day ago
AI Engineer
United States
Full-time
Remote
Mid LevelConcentrate AI provides a unified, OpenAI-compatible API to access, route, and manage LLMs. The role involves building, running, and debugging LLM applications, working on production workloads, and collaborating with the product team to improve the platform.
Computer Software
Responsibilities
Build LLM-powered services, workflows, and applications using Concentrate
Integrate with real production applications and environments
Design reliable interactions with LLMs (OpenAI, Anthropic, Gemini, OSS), including prompts, tool calling, evals, and guardrails
Debug failures across models, APIs, and infrastructure
Write code, scripts, and small tools to test system behavior at scale
Reproduce bugs, isolate root causes, and clearly document findings
Drive improvements to APIs, defaults, and overall developer experience
Qualification
Required
Hands-on experience integrating LLMs via APIs in production
Always building tools, scripts, side projects, or experiments to test ideas and learn fast
Strong Python; TypeScript is a plus
Comfortable with REST APIs, async systems, and production debugging
Curious about model behavior under load, failure, and edge cases
Familiarity with tool calling, agents, multi-step workflows, or MCPs
Strong code quality and technical judgment
Comfortable operating in early-stage environments with speed and ambiguity
Clear async communication (Slack, written updates, concise docs)
Fluent written and verbal English required for documentation, incident response, and technical and business presentations
Preferred
Bonus: active open-source contributor
Company
Concentrate AI
It should be easy to use any LLM you want. That's why we're building Concentrate. One API for all models across all providers.
Founded in 2025
2-10 employees
Funding
Current Stage
Early StageCompany data provided by crunchbase