Ruby Labs 3 дня назад
AI Engineer
- Удалённо
AIPostgreSQLTypeScriptLLMNode.jsRAGLangfuseCloudflare Workers
Описание
Responsibilities
- Take ownership of major AI features and LLM workflows and deliver them to production within agreed timelines.
- Own AI output quality, structure and predictability across user-facing AI interactions, with consistent structured output across different LLMs for the same request type.
- Integrate and orchestrate multiple LLM providers through an AI gateway, managing model selection, fallback strategies and cost optimisation.
- Design and orchestrate tool-using and agentic AI workflows: clean tool contracts (including MCP-based tools), function-calling interfaces and reliable AI-to-system integrations.
- Build and maintain multi-step LLM workflows and RAG pipelines (indexing, embeddings, retrieval, re-ranking) for reasoning, context reuse and search.
- Design and manage production prompt systems with dynamic prompting, context injection, and conditional logic.
- Own prompt management, the release of LLM experiments and Langfuse-based evaluation pipelines: test datasets, LLM-as-a-judge, output scoring.
- Run A/B tests across models and prompts, analyse the results and present the data-driven impact of AI features and experiments.
- Deep-debug LLM chains using Langfuse traces: identify bottlenecks, optimise for cost, latency and context-window usage, and root-cause hallucinations and logic errors.
- Write clean, scalable and maintainable TypeScript across the Node.js / Cloudflare Workers stack.
- Build reliable backend logic for AI systems: request and output validation, error handling, fallback flows for malformed or low-quality model responses, and reliable tool execution.
- Ensure high code quality through tests (including validation and fallback paths for AI output), code reviews and clear engineering standards.
- Monitor AI system metrics, quality signals, latency and release health, and resolve production issues with a documented root cause.
- Document prompt designs, model and routing choices, evaluation results and architectural decisions, so others can pick up the work.
Requirements
- 4+ years of backend/fullstack software engineering experience, with production-grade TypeScript/Node.js.
- 1+ year of AI/LLM systems in production with real users, not only side projects or experiments.
- Daily use of AI-centred development tools (Claude Code, Cursor or similar).
- Deep hands-on experience with LLM APIs (OpenAI, Anthropic, Google Gemini or similar) in production: structured output, function calling, streaming, token and cost control.
- Experience with agentic AI, multi-step orchestration, tool-based workflows (function calling / tool execution) or RAG pipelines (indexing, retrieval, re-ranking).
- Experience with LLM observability and evaluation tools (Langfuse, LangSmith or similar).
- Experience with AI gateways and model routing (OpenRouter, Cloudflare AI Gateway or equivalent).
- Solid understanding of relational databases (PostgreSQL) and caching (Redis, KV or similar).
- Exceptional ownership and personal responsibility for engineering quality and delivery.
Nice to have
- Evaluation frameworks (LLM-as-a-judge, RAGAS) and building test datasets.
- MCP (Model Context Protocol): building MCP servers/clients or designing tool contracts for AI agents.
- Edge/serverless runtimes (Cloudflare Workers) and their services: KV, Durable Objects, Queues, R2, Containers.
- Search engines and vector search (OpenSearch, Elasticsearch, pgvector), embeddings.
- Background workflow engines (Hatchet, Temporal, Inngest) for high-volume LLM pipelines.
- Browser automation and browser agents (Playwright, CDP, browser-use).
- Practical fine-tuning for domain-specific tasks or strict JSON/schema compliance.
- Working Python for data science, evaluation scripts, or AI tooling.
We offer
- Remote Work Environment: Embrace the freedom to work from anywhere, anytime, promoting a healthy work-life balance.
- Unlimited PTO: Enjoy unlimited paid time off to recharge and prioritize your well-being, without counting days.
- Paid National Holidays: Celebrate and relax on national holidays with paid time off to unwind and recharge.
- Company-provided MacBook: Experience seamless productivity with top-notch Apple MacBooks provided to all employees who need them.
- Flexible Independent Contractor Agreement: Unlock the benefits of flexibility, autonomy, and entrepreneurial opportunities. Benefit from tax advantages, networking opportunities, reduced employment obligations, and the freedom to work from anywhere.
Hiring process
- After submitting your application, we conduct a thorough review which typically takes 3 to 5 days, but may occasionally take longer due to the volume of applications received.
- If we see a potential fit, we proceed with the following steps:
- Recruiter Screening (40 minutes)
- Technical Interview (90 minutes)
- Final Interview (60 minutes)