About the Role
You'll be the Tbilisi seat for agent orchestration depth, paired daily with our Lisbon Agentic Engineer as your remote tech lead. Day-to-day, you'll ship production multi-agent systems for enterprise clients (orchestration topology, tool ecosystem, agent memory, human-in-the-loop checkpoints, observability) and contribute substantively to our reusable agent orchestration framework that future Agentic Engineers across all sites will build on.
The bar at 12 months is 2+ production multi-agent systems shipped for enterprise clients, plus at least 3 framework-level commits merged into the shared orchestration framework.
In Phase 1, this role is internal-facing. Client-facing engagement opens in Phase 2 once Tbilisi has a 12-month delivery track record.
This is engineering, not research. We ship.
What You'll Do
You'll ship 2+ production multi-agent systems used by enterprise clients (deployed, signed-off via the Lisbon or DACH frontstage, in active use as AUTOMATE-layer engagements)
You'll contribute substantively to our reusable agent orchestration framework: at least 3 framework-level commits or modules merged within 9 months
You'll take ownership of at least 1 production agent within 6 months of joining, paired with the Lisbon Agentic Engineer for handover
You'll apply our agent quality bar to every shipped system: documented orchestration-level evals, rollback plan, incident playbook, observability instrumentation
You'll maintain ≥ 60% billable utilisation on internal AUTOMATE projects or client engagements via the Lisbon/DACH frontstage from month 6 onward
You'll co-author 1+ public-facing technical asset (blog post or webinar) on our multi-agent architecture approach
You'll contribute to AUTOMATE-layer scoping conversations as the technical authority on the Tbilisi side, via the Lisbon or DACH frontstage
What You Bring
Must-haves
3 to 6 years shipping production AI systems beyond notebooks. You can walk us through what you shipped, what broke, and how you fixed it
Either personally shipped multi-agent systems to production, OR shipped sophisticated single-agent systems plus 1 to 2 framework-level multi-agent projects. You can articulate when to use one agent vs. many, and the tradeoffs
Hands-on experience with at least one major agent framework (LangGraph, LangChain, AutoGen, CrewAI, Semantic Kernel, Pydantic AI, Mastra, or comparable)
Track record of long-running agent loops (10+ steps) holding up in production: state management, retry policies, max-step caps, looping detection, graceful recovery from tool failure
Production fluency with agent observability and tracing (LangSmith, Helicone, Arize, Langfuse, or self-built). You read traces like an SRE reads CPU
Strong Python or TypeScript with tests, types, CI, deployment in cloud (AWS, GCP, or Azure), Docker, and basic IaC
Demonstrated async cross-site collaboration: PR, Jira, Confluence quality that removes sync follow-up
Business-fluent English (daily working language across all sites)
Tbilisi-based or willing to relocate, with sustainable 5-hour CET overlap commitment
Genuine excitement to ramp on our chosen agent framework stack during the 6 to 8 week probation period
Nice-to-haves
Public open-source contributions to agent frameworks
Direct HubSpot or comparable CRM integration experience
Eval engineering background at the orchestration level
Experience as a senior anchor in a hub or site that was being built from scratch
Your Team
You'll report directly to the Director Development & Technology, with day-to-day pairing with the Lisbon Agentic Engineer (remote tech lead) and a dotted line to the Head of AI & Agentic Delivery once that hire is in seat. You'll join the AI Team as the Tbilisi seat for agent orchestration depth.
Tech Stack
Languages: Python and TypeScript
Agent frameworks: LangGraph, LangChain, AutoGen, CrewAI, Pydantic AI, Mastra (we pick per engagement)
LLMs: Anthropic Claude (we are an Anthropic Build Partner), OpenAI, Gemini, with self-hosted options where the engagement demands it
Observability: LangSmith, Helicone, Langfuse, Arize
Cloud and DevOps: AWS, GCP, Azure, Docker, GitHub Actions, basic IaC
CRM and integration: HubSpot APIs (REST, GraphQL, webhooks)
Collaboration: Jira, Confluence, Forecast, Claude AI, Claude Code, Cursor
What We Offer
Employment & Statutory: Compliant Georgian employment via Remote.com EOR (paid time off, public holidays, parental leave, statutory health coverage), salary paid in EUR
Health: Private health insurance top-up on top of statutory coverage
Learning: Full Blinkist Business library (4,500+ books), 3 months of Babbel, dedicated AI conference and certification budget
Flexibility: Remote-first setup with Tbilisi hub access, daily CET overlap (5 hours minimum)
Culture & Tools: Flat hierarchies with direct line to Director D&T and Leadership, modern stack (HubSpot, Jira, Confluence, Claude AI), Anthropic Build Partner status with early access to Claude capabilities
About Thorit
Thorit is one of Europe's leading HubSpot partners and a top business and technology consultancy. We combine strategic advisory with hands-on IT implementation, from CRM architecture to fully automated go-to-market infrastructure powered by AI and agentic systems.
Ready to Apply?
Send your application via Ashby. A cover letter is optional, but a concrete example of an agent system you have personally shipped (architecture, framework choice, orchestration topology, what broke and how you fixed it) is required. Public links (GitHub, blog post, demo video) very welcome.
Other open roles at Thorit(6)
Experten für CRM & HubSpot – Wir optimieren Ihr digitales Wachstum mit individuellen CX-Strategien & IT-Lösungen für nachhaltigen Erfolg. 🚀
Key team members

Steffen Papke

Axel Jahn

Michael Huber

Simon Thalheim
Jobr aggregates jobs directly from company career portals — no middlemen. Our team applies on your behalf with AI-tailored resumes, reviewed by a human before submission.