AI Engineer (LLM)

TL;DR

AI Engineer (LLM): Building and productionizing multi-agent workflows and hybrid retrieval systems with an accent on knowledge graphs, vector search, and LLM orchestration. Focus on taking agent architectures from prototype to production, ensuring reliability, and building evaluation harnesses for quality, latency, and cost.

Location: Must be based in Europe

Company

hirify.global is a product company focused on building advanced AI-driven platform solutions.

What you will do

• Build and productionize multi-agent workflows using Anthropic and OpenAI APIs.
• Design hybrid retrieval architectures combining knowledge graphs, vector search, and ranking.
• Develop evaluation harnesses and observability tools to monitor agent behavior, latency, and cost.
• Integrate LLM inference and reasoning services into production backends.
• Collaborate with researchers to transform neuro-symbolic prototypes into robust product features.

Requirements

• Must be based in Europe
• 4+ years of software engineering experience in backend or ML with Python.
• Hands-on experience building LLM systems including agents, tool use, RAG, or evaluation pipelines.
• Proven experience with OpenAI or Anthropic APIs in production environments.
• Strong engineering fundamentals in API design, service architecture, testing, and deployment.

Nice to have

• Experience with structured knowledge representations like ontologies, SPARQL, or Neo4j.
• Knowledge of vector databases and hybrid retrieval architectures.
• Experience with Kubernetes and cloud-native deployment.
• Familiarity with model serving frameworks like vLLM, fine-tuning, or evaluation frameworks.
• Proficiency in Go or Scala.