Principal Al Engineer - India

Who We're Looking For Cornerstone is seeking a Principal AI Engineer to set the technical direction for the Architecture team that forms the backbone of our Cornerstone AI Platform. This is a high-ownership, high-influence role where you will architect the platform's core AI building blocks: the LLM Platform, RAG and Vector DB retrieval, the Agentic Platform and MCP integration, Message Streaming, API Gateway design, voice-based role-play assistants, and the Eval framework that every AI capability across the product suite depends on. Your design decisions shape how AI is built, scaled, and validated across the entire Cornerstone product line. You will set architecture standards and patterns that applied ML and product teams build on top of, drive end-to-end implementation of production-scale platform components, and mentor and level up the senior engineers around you. If you want to work at the intersection of modern GenAI platform engineering and see your architecture power features used by a global workforce. In This Role You Will... Define and own the architectural foundation for the Cornerstone AI Platform, including authentication and authorization, API Gateway design, and the standards and patterns every AI service is built on. Architect and operate a multi-tenant LLM Platform used by multiple product teams, covering model routing, prompt versioning, guardrails, observability, and cost governance

• Build and improve RAG pipelines: chunking strategy, embedding, Vector DB retrieval, generation, hallucination reduction, knowledge freshness, and multi-tenant data isolation. Design and deploy the Agentic Platform and MCP integration layer, defining how agents plan, call tools, recover from failures, and connect securely to internal and partner systems. Design voice-based role-play assistants end-to-end and define quality metrics: WER, intent accuracy, turn latency, and task completion rate. Own the AI Evaluation Platform, covering offline and eval frameworks, regression detection pipelines, and the quality metrics every AI capability is measured against. Contribute to and extend the Message Streaming Platform that processes internal and external events across microservices at scale. Lead solution design for new AI services, set reusable patterns and cross-team standards, and build cross-functional alignment across product, operations, database, and security teams. Mentor senior engineers, conduct design reviews, and raise the technical bar across the team. You've Got What It Takes If You Have... 8+ years of backend engineering experience in Java (Spring / Spring Boot) and/or Python. Deep, hands-on experience architecting, building, and operating production-grade AI/ML and GenAI systems at scale. Proven depth in RAG pipelines, Vector DBs, LLM platforms, Agentic platforms and agents, MCP integration, voice-based assistants, and Eval frameworks and metrics. Strong cloud fundamentals on AWS (EKS/Kubernetes, IAM, DynamoDB, RDS, KMS, S3) and infrastructure-as-code (Terraform). Expert-level API and platform design, including versioning, backward compatibility, multi-tenant isolation, and rate limiting. Proficiency across SQL (RDS), NoSQL (DynamoDB), Vector DBs, and caching (Redis)
• Demonstrated technical leadership: setting org-wide architecture standards, driving cross-team alignment, and mentoring senior engineers. Bachelor's, Master's, or PhD in Computer Science, Engineering, Machine Learning, or a related field (or equivalent experience). #LI-onsite