> Markdown version of [/jobs/ext/1997947-ai-architect-ua-ru-language-speaking](https://www.wearedevelopers.com/jobs/ext/1997947-ai-architect-ua-ru-language-speaking). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Ai Architect (Ua/Ru Language Speaking)

- **Company:** Neurons Lab
- **Location:** Madrid, Spain
- **Contract:** Temporary contract
- **Skills:** Artificial Intelligence, Amazon Web Services, Data Governance, Python (Programming Language), Machine Learning, Neo4j, Scrum Methodology, Role-Based Access Control, Systems Architecture, Microsoft Power Automate, Large Language Models, Model Validation, Amazon Virtual Private Cloud (VPC), Data Layers, Hubspot
- **Published:** August 9, 2026
- **Apply:** https://www.buscojobs.com.es/ai-architect-ua-ru-language-speaking-en-madrid-ID-366226522

## About the Role

architecture end to end: retrieval, tools, orchestration, memory, evals, guardrailsOntology / knowledge-graph engineering and semantic layers over heterogeneous sources (RDF/OWL, Neo4j, dbt-style modelling - pragmatism over purity)RAG / GraphRAG at production quality, including hybrid retrieval and permission-aware retrievalMCP, tool-calling and connector platforms; designing agents that perform actions with side effects safelyPrivate / sovereign deployment: VPC, on-prem, self-hosted or open-weight models; AWS and/or GCP data + AI stackIdentity, access control and data governance applied to AI systems (RBAC/ABAC, scoping, audit)Strong hands-on Python; comfortable writing thehard 20% of the code yourselfEvals & observability for LLM systems; treating quality as measurable, not anecdotalAdvanced written and spoken English; can hold an architecture conversation with a CIO and a CISO in the same meetingKnowledge The current enterprise context-layer landscape -
Glean-class platforms, Cohere-class "AI OS" products, Microsoft Copilot / Agents, Gemini Enterprise, Palantir-style foundries - and where each genuinely differsGDPR and data-residency constraints for multi-jurisdiction European groups; what makes a private deployment defensibleFinancial services / private-equity context - investment policy, portfolio reporting, board process - a strong plusOKR / goal-management mechanics, enough to architect for themExperience 7+ years hands-on AI/ML engineering, of which 2+ years building LLM / agentic systems in production3+ years as technical lead or architect on client-facing deliveryDemonstrated ontology / knowledge-graph or semantic-layer work over messy real-world enterprise dataExperience with regulated or security-sensitive clients (BFSI, government, healthcare) and private deploymentExperience in consulting or a services business - comfortable being the technical face to a C-level clientComfortable as the
most senior technical person on a 2.5-FTE pod, with founders as sparring partners rather than a safety net#J-*****-Ljbffr

## Description

Join Neurons Lab as the AI Architect on a flagship engagement with a European private investment group - a holding company with a C-level executive team, an investment/portfolio function and an affiliated family office.The programme builds one private, access-scoped context layer over the group's data - calls, email, Slack and messengers, board protocols, decks, portfolio updates - and then AI skills and agents that run on it : first for the executive team, then for every employee.Two loops sit on the same layer: alignment (strategy, OKRs and goal drift made visible) and efficiency (a process miner that reads real workflows from the digital footprint, then optimizer agents that ship the automations).Four phases - Capture ? Connect ? Distill ? Build - over roughly eight to ten two-week sprints, opening with a fixed-fee two-week Sprint 0 readiness pass (data-access audit, ontology spec, legal checklist across jurisdictions).A family-office workstream runs in parallel on the same squad.This is deliberately not a wrapper around an off-the-shelf platform.The client wants infrastructure they own, deployed privately, with role-based access for people and full visibility for the AI.The same architecture becomes a NeuronsLab product line, so you are designing something that has to survive being redeployed for the next client.Stage: pre-contract / design-partner negotiation.Duration: multi-phase, ~4-5 months to production for the executive pilot, with rollout beyond it.Reporting: CTO (@Alex Honchar) and CEO are in the room at every key point - architecture, sprint planning, sprint reviews.You own the technical decisions between those points, working alongside an AI Analyst (1.0 FTE) and a Data Engineer (0.5 FTE), plus the client's Head of Security from day one.This role is full-time.What You'll Actually Do (example Tasks) Run the Sprint 1 decision spike and write the decision record: one central private-cloud store vs. a semantic layer over the existing systems of record vs. ready platforms (Gemini Enterprise, Glean-class, Cohere-class, open components) - scored on security, access control, speed, cost and reversibility.Design the ontology / semantic layer for the group: entities, relationships and business definitions spanning people, meetings, decisions, commitments, goals, deals, portfolio companies and documents.Architect the connector layer as an execution layer, not just an ingestion layer - MCP / tool-calling (Composio-class or built) so agents can act in HubSpot, mail, Slack and internal systems, not merely read a stream of data.Design role-scoped retrieval: the principle is that AI sees everything and people keep role-based access.Make that enforceable at the retrieval layer, not just in the UI, and evidence it to the client's security function.Architect the agent layer: per-executive skills (Chief of Staff / CIO / CFO / COO), the OKR & drift coach delivered in Slack, and the process miner ? optimizer chain.Choose and stand up the private deployment - VPC / on-prem / managed, model selection and routing, cost and latency envelopes.Build the eval and observability harness: correctness, groundedness, access-boundary tests, regression suites before anything reaches an executive.Establish standards and failure-mode design - human-in-the-loop boundaries for agents that take real actions, audit trails, rollback.Stay hands-on: implement the critical pieces yourself, review the pod's work, and keep the build portable enough to redeploy as a NeuronsLab offering.Explain all of the above to a C-level audience in plain language, in review sessions and working groups.Skills Agentic system architecture end to end: retrieval, tools, orchestration, memory, evals, guardrailsOntology / knowledge-graph engineering and semantic layers over heterogeneous sources (RDF/OWL, Neo4j, dbt-style modelling - pragmatism over purity)RAG / GraphRAG at production quality, including hybrid retrieval and permission-aware retrievalMCP, tool-calling and connector platforms; designing agents that perform actions with side effects safelyPrivate / sovereign deployment: VPC, on-prem, self-hosted or open-weight models; AWS and/or GCP data + AI stackIdentity, access control and data governance applied to AI systems (RBAC/ABAC, scoping, audit)Strong hands-on Python; comfortable writing thehard 20% of the code yourselfEvals & observability for LLM systems; treating quality as measurable, not anecdotalAdvanced written and spoken English; can hold an architecture conversation with a CIO and a CISO in the same meetingKnowledge The current enterprise context-layer landscape - Glean-class platforms, Cohere-class "AI OS" products, Microsoft Copilot / Agents, Gemini Enterprise, Palantir-style foundries - and where each genuinely differsGDPR and data-residency constraints for multi-jurisdiction European groups; what makes a private deployment defensibleFinancial services / private-equity context - investment policy, portfolio reporting, board process - a strong plusOKR / goal-management mechanics, enough to architect for themExperience 7+ years hands-on AI/ML engineering, of which 2+ years building LLM / agentic systems in production3+ years as technical lead or architect on client-facing deliveryDemonstrated ontology / knowledge-graph or semantic-layer work over messy real-world enterprise dataExperience with regulated or security-sensitive clients (BFSI, government, healthcare) and private deploymentExperience in consulting or a services business - comfortable being the technical face to a C-level clientComfortable as the most senior technical person on a 2.5-FTE pod, with founders as sparring partners rather than a safety net#J-*****-Ljbffr


## Related Videos

- [When Should You Use an Agent? Architectural Trade-offs in Agentic Systems](https://www.wearedevelopers.com/videos/100109-when-should-you-use-an-agent-architectural-trade-offs-in-agentic-systems)
- [Why Your AI Agent Keeps Hallucinating Your Data: Building Deterministic Context Layers](https://www.wearedevelopers.com/videos/2055-why-your-ai-agent-keeps-hallucinating-your-data-building-deterministic-context-layers)
- [Integrate your Cognitive Assistant with 3rd-party DBs and software](https://www.wearedevelopers.com/videos/249-integrate-your-cognitive-assistant-with-3rd-party-dbs-and-software)
- [Putting the Graph In GraphQL With The Neo4j GraphQL Library](https://www.wearedevelopers.com/videos/257-putting-the-graph-in-graphql-with-the-neo4j-graphql-library)
- [The Missing Layer Between Enterprise Data and AI Agents](https://www.wearedevelopers.com/videos/100286-the-missing-layer-between-enterprise-data-and-ai-agents)
- [How to govern Vibe Coding for the Enterprise](https://www.wearedevelopers.com/videos/100290-how-to-govern-vibe-coding-for-the-enterprise)

## Related Articles

- [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering)
- [Everything a Developer Needs to Know About MCP with Neo4j](https://www.wearedevelopers.com/magazine/604-everything-a-developer-needs-to-know-about-mcp-with-neo4j)
- [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this)
- [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix)
- [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)
- [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)