- Location
- Noida, India
- Workplace
- Remote
- Department
- Engineering
- Source
- Keka
Description
Role Overview
We are looking for a hands-on Software Architect to own the end-to-end architecture of a multi-tenant AI platform, including the integration bus, semantic layer, agent runtime, workflow engine, and data stores. The role requires expertise in distributed systems, enterprise integrations, AI agents, scalability, and security.
Key Responsibilities
- Own the target architecture and architecture decision records (ADRs).
- Finalize the durable workflow engine, tenancy model, and data-store boundaries within the first two weeks.
- Design and build the semantic resolution engine with AI engineers, translating plain-language definitions into systems, tools, and access rights.
- Define API contracts, event schemas, adapter contracts, supervisor graph state schemas, and security standards.
- Conduct design reviews, unblock engineers, and review critical code.
- Own scalability, tenant isolation, latency, data retention, disaster recovery, and load testing.
- Ensure the platform supports up to 10,000 concurrent runs.
- Collaborate with pilot customers' architects and security teams.
Required Skills & Qualifications
- Experience designing and shipping scalable, multi-tenant SaaS or platform products.
- Strong knowledge of distributed systems, durable workflows, sagas, Kafka, idempotency, back-pressure, and failure handling.
- Expertise in relational, in-memory, and vector databases.
- Production experience with LLM-based systems, tool calling, agent orchestration, LangGraph or equivalent frameworks, RAG, and evaluation.
- Enterprise integration experience with CRM, ERP, and legacy systems using REST, SOAP, JDBC, and file-based integrations.
- Strong understanding of B2B security architecture, RBAC, tenant isolation, secrets management, and PII handling.
- Hands-on coding experience and the ability to make and explain critical architecture decisions.
Good to Have
- Production experience with Temporal.
- Experience with Apache Camel or similar integration frameworks.
- Kubernetes operations at scale.
- Published technical talks, research papers, or open-source contributions.
Key Focus Areas
- Multi-tenancy and enterprise security
- Distributed systems and durable workflow execution
- AI agents, semantic resolution, and RAG
- Enterprise integrations and data architecture
- Scalability, reliability, and disaster recovery
Skills
KubernetesRESTERP