Senior Data Engineer

• Architect the intelligence engine. Help architect and build the core engine that turns connected financial data into grounded, deterministic answers. Design the structured knowledge layer: how facts, relationships, and context are associated and queried. Build deterministic reasoning paths that produce computed, reproducible results with a clear chain back to source data. Define the interfaces between the engine and the data, model, and conversational layers, and author architecture decision records (ADRs) for the AI layer.
• Design the conversational and agentic layer. Design the conversational AI agents that serve answers to finance users. Build agentic orchestration (e.g. Lang Graph) that interprets intent, calls the engine and tools, and assembles a response, with explicit verification and human-confirmation checkpoints. Keep the agent layer a thin, auditable interface: it routes and narrates, the engine supplies the substance. Design fallbacks and targeted clarifying questions for when context is genuinely missing.
• Make grounding and determinism a hard gate. No fabricated or unsupported output, ever. Use structured output, retrieval grounding, and guardrails so generated text only states what is supported by verified data or confirmed by a human. Engineer for reproducibility in answer generation despite probabilistic models underneath, and partner with the Evaluation Rig to gate faithfulness, hallucination, and grounding in CI.

Build for multi-cloud, in-VPC deployment. Design the AI layer to run inside the customer's environment across AWS, Azure, and GCP. Integrate managed LLMs in-VPC (Amazon Bedrock, Google Vertex AI, Azure OpenAI) so data never leaves the customer boundary. Partner with Platform Engineering on model serving, scaling, and cost-aware inference, and account for single-tenant and on-premises constraints in every architecture decision.

Provide technical leadership. Set direction and standards for the engine and agent layer. Mentor AI and backend engineers and lead design and architecture reviews. Partner closely with US-based AI leadership and the Staff AI Engineer to stay aligned on vision and rigor, and translate strategy set in the US into well-architected execution offshore.

• A note on accountability: this role owns the architecture of the intelligence engine, the conversational agent layer, and the grounding and determinism guarantees of the AI layer. It does not own the application and API services layer, the data foundation, model serving infrastructure (owned with Platform Engineering), or product prioritization.

The AI Architect owns the architecture of the intelligence engine at the core of the platform, and the conversational AI agents that sit on top of it and serve answers deterministically.

The engine turns connected enterprise data into answers that are computed, reproducible, and traceable to verified source data, not improvised by a model. The agents interpret what a user is asking, route it to the engine, and present the result in natural language without ever inventing the substance of the answer.

Our output sits adjacent to externally reported financials.  Sounds plausible  is never good enough. The same question against the same data must return the same grounded, explainable answer, and every answer must trace back to its source data and the logic that produced it, because our customers' auditors will ask. That is not a guardrail you bolt on later. It is a product requirement, and it shapes how the engine and agents are designed from the first commit.

The AI layer also deploys inside customer clouds, including managed LLMs in-VPC, so customer data never leaves their environment.

This is a deeply hands-on architecture role. You set technical direction for the engine and agent layer, partner closely with US-based AI leadership and the Staff AI Engineer on grounding and evaluation rigor, and raise the bar for how deterministic, auditable AI gets built across the team.

• An intelligence engine that turns connected financial data into deterministic, traceable answers: the same question against the same data returns the same result, every time.
• A conversational agent layer that interprets questions and narrates engine output without inventing substance.
• Grounding and faithfulness gated in CI, with reproducible answer generation despite probabilistic models underneath.
• An AI architecture that runs in-VPC across AWS, Azure, and GCP, including…