Intelligence & Data Architect - Contract - London 5 days per week on site
Posted 1 week ago by Robson Bale Ltd
£900 Per day
Inside
Onsite
London - Full time on site, UK
Summary: The Intelligence & Data Architect role involves designing a multi-service platform for financial analysis and AI-assisted investment advisory, utilizing technologies such as Snowflake and Neo4j. The position requires hands-on involvement in the architecture and governance of the system, ensuring coherent contracts and verification paths across various layers. The role is based in London and requires full-time on-site presence. The successful candidate will work closely with engineering, compliance, and clients to deliver a robust MVP for an enterprise asset-manager client.
Key Responsibilities:
- Own the end-to-end design from raw data to AI advice, ensuring coherent contracts and verification paths.
- Ship hands-on, slice by slice, while maintaining defensible architecture decisions and governance posture.
- Collaborate with engineering, compliance, and clients to deliver a multi-service platform.
Key Skills:
- Hands-on software/data systems development with Python (FastAPI, asyncio, pytest).
- Deep data architecture knowledge including ontology, taxonomy, and data contracts.
- Experience with Neo4j for knowledge graph design and dual-graph implementation.
- Domain-specific language design and implementation skills.
- AI agent orchestration and responsible AI governance experience.
- Cloud data platform integration, particularly with Snowflake and AWS.
- Strong written communication skills for documentation and governance.
Salary (Rate): £900 daily
City: London
Country: UK
Working Arrangements: on-site
IR35 Status: inside IR35
Seniority Level: undetermined
Industry: IT
Detailed Description From Employer:
Intelligence & Data Architect - Contract - London 5 days per week on site
£900 per day via umbrella
5 days per week on site in central London
About the Project
Building a multi-service platform for financial analysis, portfolio construction, and AI-assisted investment advisory. It pairs a Snowflake-backed data lake with a Neo4j dual-graph (domain ontology + lexical/GraphRAG) so portfolios, instruments, and unstructured research can be queried through one financial DSL. On top of that data substrate sits R.ai, a governed LLM advisor with capability boundaries, approval gates, disclosure, and full audit chains, exposed via streaming chat and voice. The Front End (React/TypeScript monorepo) and Back End (FastAPI services on EKS, deployed via Helm and ArgoCD) are wired together with PBAC, OTEL, and a strict ADR/RFC governance process. The platform is in MVP delivery for an enterprise asset-manager client.
Mission
Own the end-to-end design from raw data to AI advice: ensure every layer - data assets ? ontology/dual-graph ? financial DSL ? LLM gateway ? tool gateway ? agent ? UX - has a coherent contract, an ADR behind it, and a verification path (formal, runtime, audit). Ship hands-on, slice by slice, while keeping the architecture decisions, ontology, and governance posture defensible to engineering, compliance, and the client.
Required Qualifications
- Building software/data systems with hands-on Python (FastAPI, asyncio, pytest, type hints, monorepo discipline)
- Deep data architecture: ontology, taxonomy, conceptual/logical/physical modeling, data contracts, gap analysis
- Knowledge graph design with Neo4j - dual-graph (domain + lexical), Cypher, sizing (Aura), node/edge versioning, GraphRAG patterns
- Domain-specific language design and implementation - grammar, type system, semantic mapping validator, executor, YAML/DSL pipelines
- AI agent orchestration - LLM gateway, tool gateway, streaming (SSE + WebSocket), agent ? platform contracts, agent SDKs
- Responsible AI governance - capability boundaries, approval gates, disclosure, audit chains to a graph, regulatory T-control traceability
- PBAC + RBAC, JWT auth, security-context propagation, secrets handling, SAST hygiene
- Cloud data platform integration - Snowflake (key-pair auth, schema sync), AWS (EKS, IAM, ALB), Helm, GitOps (ArgoCD)
- ADR/RFC authorship and governance - proposed ? accepted ? superseded lifecycle, registry stewardship, Confluence ? Git sync
- Test discipline - unit + integration + UAT/BDD with enforced coverage thresholds (= 90 %)
- Strong written communication - ADRs, RFCs, glossary, AGENTS.md, demo playbooks
Desired Experi
- Formal methods - Alloy/TLA+/model checking for high-assurance components
- Voice/multimodal AI - STT/TTS via Bedrock or OpenAI, WebSocket pipelines, advisory modality design
- Information architecture for documentation - Diataxis, AGENTS.md hierarchy, archival and supersession strategies
- AI-tooling fluency - Cursor agent skills, MCP servers, prompt engineering, glab/jira CLI automation
- Compliance frameworks - regulatory traceability matrices, red-team/adversarial test design
- Observability - OTEL traces, Phoenix/Grafana, structured logging with rotating handlers
- Modeling languages and ontologies beyond Neo4j (RDF/SHACL, SKOS, financial taxonomies)
- GitOps/CI quality gates - Bandit, Radon complexity, Angular commit convention, MR review automation
Desired Experiences
- Productizing an AI advisor for regulated finance - disclosure ? capability refusal ? human approval ? audit chain, with a compliance-narrator demo to a regulator-style audience
- Migrating a prototype DSL or graph to production - forward-pipeline cutover, mapping validator, deprecation of Legacy entry points without breaking labs notebooks
- Owning a service from blank repo to client demo - bootstrap, config, health, auth ? LLM gateway ? tools ? governance ? voice ? Helm chart, all in measurable slices
- Running architecture governance for a multi-service platform - 10+ ADRs across data, infra, agents; multiple RFCs; superseding outdated decisions cleanly
- Building a data-MVP from scratch - scoping data assets (eg EODHD, FactSet, Macrobond), mirroring prod schemas in dev, onboarding new vendors via DSL mapping
- Designing human-in-the-loop AI - approval gate, advisory mode, capability boundary, voice with explicit modality consent
- Authoring agent skills/process automation that demonstrably scale a small team's throughput (Jira CLI, GitLab CLI, ADR skills, security-review skills)
- Spike-to-decision research - graph store evaluation, GraphRAG vector-store choice, formal verification of high-assurance components, data-locality strategy