Principal - Architecture

Key Responsibilities

1. GenAI Solution Architecture & SDLC Acceleration

2. Agentic Engineering & Tooling (hands-on)

• Design multi-agent systems with defined roles - orchestrator, coder, reviewer, tester agents - including task routing, state management, and human-in-the-loop checkpoints.
• Hands-on configuration and governance of GenAI developer tooling at enterprise scale: agentic coding tools - CLI-driven coding agents and AI pair-programming solutions that go well beyond autocomplete-style copilots - including tool-server (MCP) setup, custom commands, hooks, and repository context/instruction files, plus agent SDKs and orchestration frameworks.
• Design and deploy MCP (Model Context Protocol) servers to expose the customer's tools, APIs, and data sources to AI agents; apply tool-use / function-calling patterns for LLM-driven agents.
• Select and integrate foundation models (e.g., Anthropic Claude, OpenAI GPT, Gemini) via APIs or managed platforms (AWS Bedrock, Azure OpenAI / AI Foundry, Google Vertex AI); design model-tiering and routing strategies - frontier reasoning models for complex work, fast lightweight models for high-volume steps, open-weight models (Llama, Mistral) where data residency requires - balancing capability, cost, and latency.
• Deploy and operate GenAI workloads within enterprise cloud estates: private endpoints and network isolation, identity and access management, quota / rate-limit and regional-availability planning, model gateways, and cost governance (token budgeting, caching, chargeback).
• Advanced retrieval patterns: GraphRAG / knowledge-graph-augmented retrieval, text-to-SQL over enterprise data.

  3. Context Engineering & Domain Knowledge Capture

• Design and operate context engineering frameworks: repository instruction and context files, system prompts, retrieval strategies, context-window budgeting, and memory patterns - so agents carry accurate project, codebase, and domain context.
• Context engineering for business ontology: model the customer's domain as formal ontologies, taxonomies, and knowledge graphs - entities, relationships, and business rules - so agents reason over structured domain semantics, not just retrieved text.
• Model business processes as state machines: explicit lifecycle and state-transition models that let agents know where a case stands and which actions are legal - and deterministic state-machine orchestration to govern non-deterministic agent workflows.
• Capture and codify insurance domain knowledge: work with SMEs to elicit product structures, underwriting and claims rules, processes, glossaries, and regulatory constraints, and convert them into machine-usable assets - knowledge bases, taxonomies, RAG corpora, and golden datasets that ground agent output.
• Apply prompt engineering rigor: few-shot examples, chain-of-thought, structured output design, prompt versioning, and evaluation against golden datasets.

  Required Qualifications

• 12-14 years of proven experience in technology leadership / principal or application architect roles on enterprise-scale, distributed multi-tier systems.
• Strong architecture pedigree: n-tier, microservices, and event-driven architecture (EDA) design - including messaging/streaming platforms (Kafka or cloud-native equivalents) - enterprise integration, API design and management, and cloud-native delivery on AWS, Azure, or GCP (IaaS/PaaS/SaaS, containers, CI/CD).
• Deep expertise in at least one major enterprise stack (Java/Spring, .NET, Python, or Node.js) with breadth across others; working proficiency in Python for GenAI development.
• Demonstrable agentic GenAI delivery: at least one agent-assisted engineering or LLM-based solution taken into production or a serious enterprise pilot - able to walk through the architecture, trade-offs, and measured outcomes.
• Practical, current knowledge of multi-agent design, MCP, RAG variants (hybrid search with re-ranking, agentic RAG, RAG over code and structured data), embeddings/vector search, prompt and context engineering, evaluation harnesses and guardrails, and LLM limitations (hallucination, context-window constraints, cost/latency, data privacy).
• Experience leading technology-driven programs - POCs, innovation initiatives, and solution asset development - through to large-scale delivery.
• Experience practicing Design Thinking and Systems Thinking in real-world scenarios.
• Outstanding client-facing communication: proven experience engaging customer stakeholders on requirements and delivery, and explaining complex technology in an easy-to-understand way.