Senior AI Engineer (LLM/Agentic AI)

TL;DR

Senior AI Engineer (LLM/Agentic AI): Own and deliver end-to-end major AI features in production with an accent on AI output quality, reliability, and evolution across multi-step LLM workflows. Focus on integrating multiple LLM providers via OpenRouter, building tool-using/agentic systems (including MCP-based tool contracts), and running Langfuse-based evaluation and A/B testing to optimize cost, latency, and hallucination/logic-error root causes.

Location: Remote (CET time zone, applicants located within approximately ± 4 hours of CET) — European Union / Bosnia / Georgia / Moldova / Montenegro / North Macedonia / Serbia / Turkey

Company

hirify.global builds and operates consumer products across health, education, and entertainment.

What you will do

• Take complete ownership and deliver major AI engineering features within agreed timelines.
• Own AI output quality, structure, and predictability across user-facing AI interactions, including segmentation, routing, and enforcement.
• Integrate and orchestrate multiple LLM providers via OpenRouter, including model selection, fallback strategies, and cost optimization.
• Design and orchestrate tool-using and agentic AI workflows, defining clean tool contracts (including MCP-based tools) and reliable AI-to-system integrations.
• Build and maintain multi-step LLM workflows using orchestration frameworks (LangChain or LlamaIndex), including retrieval, context reuse, and advanced reasoning.
• Deploy and release LLM experiments, manage prompt systems, run Langfuse-based evaluation pipelines, and perform A/B testing with data-driven impact analysis.

Requirements

• Location/time zone: Be located within approximately ± 4 hours of CET while working remotely.
• 6+ years of backend/full-stack engineering experience with production-grade TypeScript/Node.js; experience with Next.js and/or Python is a plus.
• 2+ years of experience building AI/LLM systems in production, including deep hands-on work with LLM APIs (OpenAI, Anthropic, or similar).
• Experience with agentic AI, multi-agent orchestration, tool-based workflows (function calling/tool execution), and/or RAG pipelines (indexing, retrieval, re-ranking).
• Experience with LLM observability/evaluation tools such as Langfuse (or LangSmith) and with AI gateways/model routing like OpenRouter.
• Solid understanding of Redis and relational databases (e.g., PostgreSQL), plus strong ownership and engineering quality mindset.

Nice to have

• Experience with MCP (Model Context Protocol), including building MCP servers/clients or designing tool contracts for AI agents.
• Experience with edge/serverless runtimes (e.g., Cloudflare Workers) and supporting services (KV, Durable Objects, Queues, R2, D1).
• Experience with payments/billing/checkout flows or orchestration platforms.
• Practical experience fine-tuning models for domain-specific tasks and achieving strict JSON/schema compliance.
• Experience with evaluation frameworks such as LLM-as-a-judge and RAGAS.

Culture & Benefits

• Remote work environment with unlimited PTO and paid national holidays.
• Company-provided MacBook for employees who need it.
• Flexible independent contractor agreement option (tax advantages and reduced employment obligations) alongside full-time employment.
• Squad-based engineering structure with high ownership and disciplined release practices.

Hiring process

• Recruiter screening (40 minutes), followed by a technical interview (60 minutes).
• Second interview (30 minutes) and final interview (20 minutes).