AI Architect

Overview

Meeru AI is seeking an AI Architect to design and build the deterministic intelligence engine at the core of its finance and accounting platform, and the conversational AI agents that sit on top of it.

What you'll do

• Set technical direction for the intelligence engine and the agent layer.
• Partner closely with US-based AI leadership and the Staff AI Engineer on grounding and evaluation rigor.
• Raise the bar for how deterministic, auditable AI is built across the team.
• Architect the engine, its data interfaces, and the agent layer as one coherent, maintainable system.
• Mentor engineers, run design reviews, and turn strategy set by US leadership into well-built execution.

What you'll need

• Senior or staff-level applied AI/ML experience, including having shipped production AI systems and led the technical direction on at least one.
• Deep fluency in modern LLM patterns.
• Hands-on experience with retrieval-augmented generation (RAG), tool-using agents, and structured output (e.g., JSON schemas, function calling).
• Experience building multi-step agent workflows with LangGraph or a similar framework, including verification steps, fallbacks, and human confirmation points.
• Systems architecture experience, including documenting decisions (e.g., architecture decision records).
• Experience making "no unsupported answers" a hard rule in a real system and measuring faithfulness and hallucination with automated evaluations, ideally in CI.
• Knowledge of making the same question against the same data return the same answer, and ability to explain the techniques used.
• Clear judgment about what a model can legitimately claim in a high-stakes domain.
• Production software engineering in Python, including robust, tested services with SQL access to warehouses or databases (e.g., Snowflake, PostgreSQL) and containerized deployment.
• Working knowledge of vector stores (pgvector, Pinecone, Weaviate, or Qdrant) and of computing reliable answers over structured data.
• Strong communication skills to explain architecture trade-offs to engineers, product managers, and non-technical stakeholders in clear English.

Nice to have

• Finance, accounting, or other audited domains.
• Experience where outputs face auditors or regulators (finance, healthcare, insurance, legal).
• Experience with knowledge graphs, semantic layers, or rule/reasoning engines.
• Experience designing human-in-the-loop review, confirmation, or feedback loops.
• Hands-on experience with Amazon Bedrock, Google Vertex AI, or Azure OpenAI deployed in a customer's private network (VPC).
• Experience shipping AI to AWS, Azure, and GCP, including single-tenant and on-premises installs, and working with platform teams on model serving and inference cost.
• Experience with tracing and evaluation tooling for LLM applications.

Details

• Location: Hyderabad (preferred) or remote elsewhere.
• Must keep a few hours of daily overlap with US time zones.
• Engagement: full-time, contract, or contract-to-hire.