2 days ago
Remote, Albania +5 moreMid Level / Senior
Responsibilities
- Own major AI features and LLM workflows from design through production delivery.
- Improve AI output quality, structure, predictability, reliability, and production stability.
- Integrate multiple LLM providers through AI gateways with model selection, fallback strategies, and cost optimization.
- Design agentic and tool-using workflows, including MCP-based tool contracts and function-calling interfaces.
- Build and maintain multi-step LLM workflows and RAG pipelines covering indexing, embeddings, retrieval, and re-ranking.
- Manage prompts, LLM experiments, test datasets, evaluations, LLM-as-a-judge scoring, and A/B tests.
- Use Langfuse traces and metrics to debug bottlenecks, hallucinations, latency, cost, and context-window usage.
- Write scalable TypeScript backend logic with validation, error handling, fallback flows, tests, and code reviews.
- Monitor AI system quality, latency, release health, and production issues while documenting root causes and architectural decisions.
Requirements
- At least 4 years of backend or full-stack software engineering experience with production-grade TypeScript and Node.js.
- At least 1 year of production experience building AI or LLM systems used by real users.
- Daily use of AI-centered development tools such as Claude Code or Cursor.
- Hands-on production experience with LLM APIs including structured output, function calling, streaming, token control, and cost control.
- Experience with agentic AI, multi-step orchestration, tool-based workflows, or RAG pipelines.
- Experience with LLM observability and evaluation tools such as Langfuse or LangSmith.
- Experience with AI gateways and model routing such as OpenRouter or Cloudflare AI Gateway.
- Solid understanding of relational databases and caching technologies.
- Exceptional ownership and responsibility for engineering quality and delivery.
- Preferred experience with LLM evaluation frameworks, MCP, Cloudflare edge services, search and vector databases, workflow engines, browser automation, fine-tuning, and Python.
Benefits
- Remote work environment with applicants accepted from locations within approximately ±4 hours of CET.
- Unlimited paid time off and paid national holidays.
- Company-provided MacBook for employees who need one.
- Flexible independent contractor agreement with autonomy and location flexibility.
- Interview process includes recruiter screening, technical interview, and final interview.
Tech Stack
Categories
About Ruby Labs
Ruby Labs builds and operates direct-to-consumer mobile apps across the health, education, and entertainment categories. The privately held company, founded in 2018 and headquartered in San Francisco, develops its own products for global audiences on iOS and Android. It ships multiple apps under a single studio model and hires within roughly ±4 hours of Central European Time to support collaboration across its distributed team.