Senior Agentic / AI Engineer (Multi-Agent Systems, Production LLMs)

Location: Helsinki Onsite (Preferable), Finland & EU Remote / Hybrid

The Opportunity

Comparables.ai builds the intelligence infrastructure for financial decision-making.

We operate one of the world’s largest datasets covering 350M+ companies and power AI-driven search, peer-group identification, and market intelligence workflows. Our platform combines structured + unstructured data, semantic retrieval, and LLM-based reasoning systems.

We are hiring a senior, product-focused AI engineer to design and operate reliable multi-agent systems in production.

What You’ll Do

• Design and deploy multi-agent systems with clear orchestration, planning, execution, and reasoning layers.
• Build agent workflows using LangGraph, LangChain, or similar orchestration frameworks.
• Implement structured tool use, memory handling, and context management using MCP (Model Context Protocol) or comparable standards.
• Design robust agent orchestration architectures (task decomposition, coordination, failure recovery).
• Develop and optimize RAG pipelines combining Elasticsearch + vector databases.
• Deploy and operate open-source and local LLMs (e.g., Llama, Mistral, Mixtral) in production environments.
• Build evaluation and monitoring systems for reasoning quality, hallucination control, and performance.
• Collaborate with backend and data teams to expose AI systems via scalable APIs.
• Own AI systems end-to-end: experimentation → hardening → monitoring → iteration.

What We’re Looking For

• 5+ years in applied ML / AI engineering with production responsibility.
• Strong hands-on experience building LLM-powered systems beyond simple prompt wrappers.
• Experience designing multi-agent architectures with orchestration and reasoning loops.
• Experience with LangGraph / LangChain or similar agent frameworks.
• Experience deploying open-source or self-hosted LLMs.
• Deep understanding of:
  • Agent planning and tool-use patterns
  • RAG system architecture
  • Embeddings & vector search
  • Structured outputs and reasoning validation
  • Latency, cost, and reliability trade-offs
• Strong Python skills and production API integration experience.

Strong Plus

• Experience implementing MCP or standardized context/tool protocols.
• Familiarity with AI governance and data governance (auditability, lineage, monitoring, compliance).
• Experience building evaluation frameworks for agent reasoning quality.
• Experience working with large structured knowledge bases.

Why Join

• Build advanced multi-agent AI systems on top of a 350M+ company dataset.
• Real-world reasoning systems — not demo chatbots.
• High ownership and architectural influence.
• Work at the intersection of data scale, retrieval, and intelligent agents.
• Competitive salary.
• Strong growth opportunity in a rapidly scaling AI SaaS company.