Senior Staff Data Engineer

MeeruAI Inc.; Pleasanton (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Health coverage 50% of premiums

Flexible spending accounts

Health savings accounts with company贡献

Unlimited PTO and 12 paid holidays

401(k) with company matching

No visa sponsorship

Job summary

Meeru AI in Pleasanton, CA seeks an AI Architect to own the architecture of the intelligence engine and the conversational agents that sit on top of it, delivering deterministic, grounded answers.

You will ensure outputs are traceable to verified data, design in-VPC deployments across AWS, Azure, and GCP, and drive reproducible, auditable AI across teams.

Qualifications

• Senior or Staff-level applied AI/ML experience shipping production systems.
• Fluency in modern LLM patterns: RAG, tool-use and agents, structured output.
• Strong systems architecture capability for engine, data interfaces, and agent layer.
• Understanding determinism and grounding in high-stakes domains and auditability.
• Experience in reproducibility and grounding for probabilistic models.
• Real software engineering: robust, tested production services, not notebooks.
• Excellent communication to engineers, product, and non-technical stakeholders.
• Proficiency with Python production services and agent orchestration.

Responsibilities

• Architect the intelligence engine and core data layer with deterministic, reproducible results.
• Design conversational/agentic layer and orchestration (e.g. LangGraph) for answer assembly.
• Implement grounding gates, CI-based faithfulness checks, and audit trails.
• Deploy AI layer in-VPC across multi-clouds (AWS, Azure, GCP) and on-prem environments.
• Lead design reviews, mentor engineers, and align US leadership with offshore teams.

Skills

Senior AI/ML experience (production)

RAG, tool-use & agents, structured输出

Systems architecture

Determinism & grounding in high-stakes

Grounding, evaluation for LLM/agentic

Reproducibility on probabilisticModels

Production software engineering

Strong communication

Python production services

LangGraph orchestration

SQL (Snowflake, PostgreSQL)

Tools

LangGraph

pgvector

Pinecone

Weaviate

Qdrant

Snowflake

PostgreSQL

Job description

Key Responsibilities

• 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. LangGraph) 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 Role

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.

What Good Looks Like

• 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 single-tenant and on-premises deployments.
• Answers that hold up when a customer's auditor pulls on them, because traceability was architectural rather than retrofitted.

Required Qualifications

• Senior or Staff-level applied AI/ML experience shipping production systems, with deep fluency in modern LLM patterns: RAG, tool-use and agents, and structured output.
• Systems architecture strength. You can design the engine, the data interfaces, and the agent layer as a coherent, maintainable whole.
• Conceptual clarity on what a model can and cannot legitimately claim, and why determinism and grounding matter in a high-stakes domain.
• Demonstrated rigor on grounding, hallucination control, and evaluation for LLM and agentic systems.
• Experience designing for reproducibility and determinism on top of probabilistic models.
• Real software engineering. You ship robust, tested, production services, not notebooks.
• Strong communication. You can explain AI architecture and trade-offs to engineers, product, and non-technical stakeholders.
• Python production services and testing; LangGraph or equivalent agentic orchestration; vector stores (pgvector, Pinecone, Weaviate, or Qdrant); and SQL against Snowflake or PostgreSQL.

Nice to Have

• Finance, accounting, or other high-stakes, auditable domain experience.
• Knowledge graph, semantic layer, or reasoning-engine experience.
• Human-in-the-loop systems and feedback loops.
• Managed LLMs in-VPC (Bedrock, Vertex AI, Azure OpenAI) and multi-cloud deployment.

Technical Stack

• LLM and agents: RAG, tool-use and agents, structured output; LangGraph or equivalent orchestration; prompt engineering, templating, and guardrails; managed LLMs in-VPC (Bedrock, Vertex AI, Azure OpenAI).
• Reasoning and data: knowledge and graph modeling, context association; deterministic computation over structured data; vector stores (pgvector, Pinecone, Weaviate, Qdrant); SQL and warehouse access (Snowflake, PostgreSQL).
• Platform: production Python services and testing; containerized, customer-hosted deployment; multi-cloud model serving with Platform Engineering; observability and evaluation tooling for AI.

Benefits

• Health and wellbeing. Medical, dental, and vision insurance, with Meeru AI covering 50% of employee premiums
• Flexible spending accounts, health savings accounts with a company contribution
• Unlimited PTO and 12 paid holidays
• 401(k) with company matching

• Meeru AI does not provide immigration or visa sponsorship for this position, now or in the future, and does not take over sponsorship of an immigration case.

Background Check

Employment is contingent upon successful completion of a background check conducted after a conditional offer of employment.

Equal Employment Opportunity

Meeru AI is an equal opportunity employer.

To request an accommodation please contact [e-mail]