Agentic Architect

Key Responsibilities

• Own the end-to-end technical architecture of the agentic platform - including agent orchestration framework, HITL engine, exception routing, integration layer, intelligence services, canonical data model, and workflow state store - ensuring all components are cohesive, scalable, and multi-tenant by design.
• Define the multi-agent design patterns used across the platform - agent boundaries, tool use contracts, inter-agent communication protocols, confidence thresholds, fallback routing, and human handoff triggers - and govern their consistent application across all workflow implementations.
• Lead the design of the workflow state management architecture - covering execution context persistence, checkpointing, idempotent retries, long-running process patterns, and safe resume - ensuring finance workflows that span days or weeks behave correctly under failure conditions.
• Define the platform's multi-tenancy architecture - tenant isolation, per-client configuration, shared service design, and data segregation - so that a single platform deployment can serve multiple clients safely and efficiently.
• Establish the observability and governance architecture - structured logging, distributed tracing, model performance monitoring, SLA tracking, audit trail design, and compliance logging - ensuring the platform meets the control requirements of regulated finance environments.
• Evaluate and select foundational technologies - LLM providers, agentic frameworks (LangGraph, AutoGen, CrewAI), orchestration engines (AWS Step Functions, Temporal), vector databases, and messaging infrastructure - with clear justification for each choice.
• Lead technical design reviews and architecture governance - reviewing critical implementation decisions made by AI engineers, backend engineers, and integration engineers, and ensuring they align with the platform's intended design.
• Work directly with client technical stakeholders during pre-sales, solutioning, and delivery - explaining architectural decisions, assessing client infrastructure constraints, and adapting the platform design to client-specific requirements without compromising reusability.
• Define and enforce non-functional requirements across the platform - latency SLAs, throughput targets, availability requirements, disaster recovery posture, and security controls - and validate that the implementation meets them.
• Build and maintain the technical roadmap for the platform - sequencing capability development, managing architectural debt, and ensuring the platform evolves coherently as new workflows and client requirements are added.
• Mentor and technically grow the engineering team - establishing architecture decision record (ADR) practices, conducting design reviews, and developing engineering standards that the team follows consistently.

Preferred Qualifications

• Deep familiarity with Finance and Accounting operations - P2P, O2C, and R2R processes, exception patterns, compliance controls, and the operational metrics (STP rate, first-pass match rate, exception aging) that define platform success.
• Experience architecting RAG pipelines, vector search infrastructure, and document intelligence services for structured extraction from financial documents at scale.
• Familiarity with financial compliance frameworks - SOX 404, IFRS, or GAAP - and the implications they have for audit trail design, data retention, and control validation in an agentic context.
• Experience with architecture governance frameworks - Architecture Decision Records (ADRs), architecture review boards, and technical standards documentation.
• Prior experience in a shared services, or F&A technology consulting context - understanding how finance operations teams work and what makes a platform adoptable by non-technical operations staff.
• Contributions to open-source AI/agentic projects or published technical writing on multi-agent system design.

Required Skills

• 10+ years of software architecture and engineering experience, with at least 3 years focused on AI/ML systems and at least 2 years hands-on with LLM-based or agentic applications in production.
• Deep expertise in multi-agent system design - agent orchestration, tool use, inter-agent communication, stateful agent patterns, and human-in-the-loop architecture using frameworks such as LangGraph, AutoGen, CrewAI, or equivalent.
• Proven experience architecting event-driven, distributed systems on AWS at scale - Step Functions, SQS, SNS, EventBridge, Lambda, ECS, API Gateway, DynamoDB, Aurora, and related services.
• Solid understanding of multi-tenancy architecture patterns - tenant isolation strategies, shared service design, configuration-driven onboarding, and data segregation in SaaS platforms.
• Experience designing for compliance and auditability in regulated environments - immutable audit trails, access control models, data retention, and SOX or equivalent control requirements.
• Strong Python skills and familiarity with Node.js - sufficient to prototype architectural patterns, review implementation code critically, and validate that the team's code matches the intended design.
• Experience with MLOps and AI governance - model versioning, drift detection, evaluation pipelines, prompt management, and production monitoring for LLM-based services.
• Demonstrated ability to lead cross-functional engineering teams - setting technical direction, conducting architecture reviews, and managing architectural consistency across parallel workstreams.
• Strong communication skills - able to explain complex architectural decisions to both engineering teams and non-technical client stakeholders, and to produce clear, concise architecture documentation.
• Experience architecting platforms that serve multiple enterprise clients from a single codebase - where each client's variation is handled through configuration, not forked code.
• Demonstrated ability to make and defend technology selection decisions with clear trade-off analysis - including build vs. buy, framework selection, and infrastructure design choices.
• Hands-on experience delivering agentic or LLM-based systems in a finance, BPO, or shared services context - not just proof-of-concept projects but production deployments with real operational volume and compliance requirements.