AI Architech

Meeru AI is building an AI-native platform that transforms how finance and accounting teams operate. They connect to enterprise financial systems — ERPs, CRMs, billing platforms, HRIS — and apply machine learning to turn fragmented operational data into grounded, auditable intelligence for CFOs, controllers, and FP&A leaders. The platform deploys on customer terms — SaaS multi-tenant, SaaS single-tenant, and on-premises — across AWS, Azure, and GCP. Customers are Fortune 500 finance teams who require data isolation, auditability, and compliance.

• Senior or staff-level applied AI/ML experience with production systems.
• Deep fluency in modern LLM patterns, including retrieval-augmented generation (RAG), tool-using agents, and structured outputs (e.g., JSON schemas, function calling).
• Experience building multi-step agent workflows with frameworks like LangGraph.
• Systems architecture skills to design a coherent engine and agent layer.
• Expertise in grounding, hallucination control, and automated faithfulness evaluation.
• Knowledge of making probabilistic models deterministic.
• Strong judgment on model claims in high-stakes domains.
• Production Python software engineering with SQL (e.g., Snowflake, PostgreSQL) and containerized deployment.
• Working knowledge of vector stores (pgvector, Pinecone, Weaviate, Qdrant).
• Technical leadership and mentoring experience.
• Strong English communication skills.
• Location preference: Hyderabad or remote with daily overlap to US time zones.
• Open to full-time, contract, or contract-to-hire engagement.

Nice to have:

• Experience in finance, accounting, healthcare, insurance, or legal audited domains.
• Experience with knowledge graphs, semantic layers, or reasoning engines.
• Designed human-in-the-loop systems with review and feedback loops.
• Hands-on with managed LLMs inside customer clouds (e.g., Amazon Bedrock, Google Vertex AI, Azure OpenAI in VPC).
• Multi-cloud and on-prem deployment experience on AWS, Azure, and GCP.
• Experience with AI observability, tracing, and evaluation tooling.

• Design and build the intelligence engine core of the platform and the conversational AI agents on top.
• Set technical direction for the engine and agent layer.
• Partner with US-based AI leadership and Staff AI Engineer on grounding and evaluation rigor.
• Ensure answers are deterministic, auditable, and traceable to source data.
• Create agent workflows with verification, fallbacks, and human confirmation steps.

Based in Hyderabad (preferred) or remote elsewhere, able to keep daily overlap with US time zones. Flexible engagement type: full-time, contract, or contract-to-hire.