AI Architect

We are looking for an experienced AI Architect to join our progressive team. You’ll work with a multi-service platform designed for financial analysis, portfolio construction, and AI-assisted investment advisory. The platform combines a Snowflake-backed data lake with a Neo4j dual-graph architecture (domain ontology and lexical/GraphRAG), enabling unified querying of portfolios, financial instruments, and unstructured research through a single financial domain‑specific language (DSL). The system supports both streaming chat and voice interfaces. Responsibilities Own and drive the end‑to‑end architecture, from raw data ingestion to AI‑powered advisory outputs. Define and enforce clear contracts across all layers, including data assets, ontology and graph structures, financial DSL, LLM gateway, tool gateway, agent layer, and user experience. Design systems with strong governance, ensuring all components are backed by documented architectural decisions (ADR/RFC) and traceable justification. Build and deliver hands‑on solutions, iterating incrementally while maintaining architectural consistency and quality. Ensure all layers include robust verification mechanisms, including formal validation (where applicable), runtime checks, and auditability. Collaborate with engineering, compliance, and client stakeholders to ensure the architecture meets regulatory, technical, and business requirements. Maintain a defensible architecture aligned with responsible AI principles, including transparency, traceability, and controlled capability exposure. Requirements 7+ years of experience in AI Engineering or a related role. Strong hands‑on experience in Python development, including FastAPI, asyncio, pytest, type hints, and working within a monorepo structure. Experience designing and implementing AI agent orchestration systems, including LLM gateways, tool gateways, streaming architectures (SSE and WebSocket), and agent‑to‑platform contracts. Understanding of responsible AI governance, including capability boundaries, approval workflows, disclosure requirements, audit traceability, and regulatory control mapping. Experience working with AWS cloud platforms in production environments. Experience in rigorous testing practices, including unit, integration, and UAT/BDD testing, with enforced code coverage thresholds (≥90%). Proficiency with modern AI tooling, such as Cursor, MCP servers, prompt engineering techniques, and CLI automation tools (e.g., GitLab, Jira). Experience implementing observability using OpenTelemetry, Grafana or Phoenix, and structured logging practices. Excellent command of written and spoken English (B2+ level). Nice to have: Understanding of data architecture principles, including ontology design, taxonomy, conceptual/logical/physical modeling, data contracts, and gap analysis. Experience designing and working with knowledge graphs in Neo4j, including dual‑graph architectures, Cypher queries, graph sizing, versioning, and GraphRAG patterns. Ability to design and implement domain‑specific languages, including grammar definition, type systems, semantic validation, and execution pipelines. Familiarity with security practices, such as PBAC/RBAC, JWT authentication, security context propagation, secret management, and secure code practices (SAST). Experience integrating cloud data platforms, including Snowflake and AWS services, such as EKS, IAM, and ALB, using Helm and GitOps tools like ArgoCD. Ability to create and maintain architectural documentation using ADR/RFC processes and manage their lifecycle effectively. Knowledge of formal methods, such as Alloy or TLA+, for high‑assurance system design. Experience with voice and multimodal AI systems, including STT/TTS pipelines using platforms like OpenAI or AWS Bedrock. Understanding of modern documentation practices (e.g., Diátaxis) and structured knowledge management. Familiarity with compliance frameworks, regulatory traceability, and adversarial testing methodologies. Exposure to additional ontology and modeling standards, such as RDF, SHACL, SKOS, or financial taxonomies. Experience with CI/CD quality gates, including tools like Bandit and Radon, and automated merge request review processes. Experience building and productizing AI advisory solutions in regulated financial environments. Understanding of end‑to‑end governance flows, including disclosure handling, capability restriction, human‑in‑the‑loop approvals, and full audit chain implementation aligned with compliance requirements. #J-18808-Ljbffr EPAM Systems