AI & Agentic Systems Advisor

About Intriq
Intriq AI is an early-stage, AI-native platform that automates financial due diligence (FDD) for transaction advisory and accounting firms. Our agents take on the most data-heavy parts of a deal, such as proof of cash and trial balance analysis, turning messy, unstructured client financials into reviewable, audit-ready outputs.
We were founded by operators who spent over a decade inside FDD, Quality of Earnings and PE portfolio work. We build alongside design partners at leading advisory firms, and our product runs on agentic workflows in production today.
As we scale, the decisions we make on agent architecture, model strategy and AI infrastructure will shape the product for years. We are looking for an advisor who has made these decisions before, in production, and can help us make them well.
The role
The AI & Agentic Systems Advisor is a strategic technical advisor to Intriq's CEO and engineering leads. You will guide how we design, build, deploy and evolve our AI products, from agent architecture and model selection to orchestration, infrastructure, reliability and cost.
This is a hands-on advisory role, not a figurehead seat. You will review architecture, pressure-test technical bets, help us choose between build and buy, and share patterns that work in production AI systems. You will also help shape our AI product strategy and how we talk about our technology with customers and investors.
What you'll doAgent architecture and design
• Advise on the design of our agentic workflows, including tool use and function calling, MCP integrations, and multi-agent orchestration.
• Guide our approach to context engineering, RAG, structured outputs, memory, and human-in-the-loop review, so financial outputs stay accurate and traceable.
• Shape our LLM evaluation and observability practice, so we can measure quality, catch regressions and prove accuracy to customers.
AI stack and model strategy
• Advise on model and platform choices across Claude/Anthropic, OpenAI, AWS Bedrock, Vertex AI, and open-weight models.
• Help decide when to use agent frameworks such as LangGraph versus custom implementations.
• Guide the trade-off between managed model APIs and self-hosted open-weight models, weighing quality, latency, cost, data privacy and client requirements.
Infrastructure, MLOps and AIOps
• Guide the setup and operation of production AI systems, including hosting and serving open-weight models: inference stacks, GPU capacity, scaling, latency and cost.
• Advise on MLOps practices: model versioning, fine-tuning and evaluation pipelines, CI/CD for models and prompts, and safe rollout strategies.
• Help establish AIOps: monitoring, drift and quality detection, cost and usage tracking, alerting and incident response.
• Make sure our AI systems stay reliable, efficient and maintainable as usage and customer count grow.
Product and company strategy
• Help shape the technical roadmap and AI product strategy alongside the CEO.
• Pressure-test major technical decisions and hiring plans for the engineering team.
• Where useful, support customer, partner and investor conversations on our AI approach, security and scalability.
What you bring
• A track record of building and leading AI products that run in production, with real users and real accountability for quality.
• Hands-on depth in agentic systems: tool use and function calling, multi-agent orchestration, context engineering, RAG, structured outputs and memory.
• Practical experience with LLM evaluation and observability, and a clear view of how to measure whether an agent is getting better or worse.
• Working knowledge of the major model platforms (Anthropic, OpenAI, AWS Bedrock, Vertex AI) and agent frameworks such as LangGraph, plus the judgment to know when not to use them.
• Experience serving models in production, including open-weight models, GPU capacity planning, and managing latency and cost at scale.
• Grounding in MLOps and AIOps: versioning, evaluation pipelines, CI/CD for models and prompts, monitoring, drift detection and incident response.
• The ability to explain complex trade-offs clearly to founders, engineers and non-technical stakeholders, and to give direct, candid advice.
Nice to have
• Experience building AI for regulated or high-stakes domains such as finance, accounting, audit, legal or healthcare, where accuracy and auditability matter.
• Familiarity with enterprise requirements for AI products: data residency, SOC 2, client data isolation and model governance.
• Prior experience as a founder, CTO, or head of AI at an early-stage company.
• Experience fine-tuning models or building domain-specific evaluation datasets.
• A network across the AI ecosystem that can help with hiring, partnerships and infrastructure.

Work arrangement
Yes