Architect - Application & GenAI Systems

Position : Architect - Application & GenAI SystemsExperience : 15 to 19 YearsLocation : BangaloreJob Type : Full-timeJob Summary : We are seeking a highly accomplished and visionary Architect - Application & GenAI Systems with 1519 years of extensive experience in designing and delivering large-scale distributed backend and advanced AI systems. Based in Bangalore, this is a principal-level role responsible for defining the technical blueprint for both traditional cloud-native applications and the emerging stack of intelligent, agentic GenAI systems. The Architect will drive technical excellence, governance, and long-term system thinking across multiple engineering and AI science teams.Key Responsibilities : Core Application Architecture and Governance : - Define and evolve the overall application architecture blueprint, encompassing service boundaries, integration patterns, technical data models, and system layering for optimal scalability, maintainability, and performance.- Guide engineering teams on the mandatory adoption of modern design principles, including microservices architecture and clean architecture to ensure codebase modularity, testability, and long-term agility.- Drive architectural governance by serving as a key member of Architecture Review Boards, defining engineering standards, and ensuring technical consistency across all teams and modules.- Define and drive the adoption of rigorous coding and design guidelines, focusing on robust API design (versioning, security, discoverability) and ensuring systems are highly available, resilient, and cost-efficient.AI and Agentic System Architecture : - Architect intelligent agent systems using advanced frameworks such as LangGraph, CrewAI, AutoGen, or custom orchestrators.- Define the technical building blocks for agent orchestration, long-term memory management, RAG (Retrieval-Augmented Generation) pipelines, and effective tool use within AI agents.- Design for latency-sensitive LLM interactions, incorporating technical solutions for fallback, automatic retries, and seamless human-in-the-loop processes.- Design and implement systems responsible for managing prompt chaining, large context windows, and secure session-based memory.- Collaborate closely with AI Scientists to bridge theoretical prompt design with production reliability, traceability, and incorporating LLM observability and explainability into architectural decisions.Cross-functional Technical Leadership : - Align the technical architecture with high-level product goals, engineering constraints, and the strategic direction of AI science research.- Mentor senior engineers across the organization and lead high-leverage technical decisions, pattern adoption, and comprehensive code/design reviews.- Drive essential architecture documentation, standardization efforts, and a culture of long-term system thinking.Qualifications : - Experience : Mandatory 14+ years of experience building and architecting complex, high-scale distributed backend systems.- Microservices & API : Deep hands-on experience in microservices design patterns, service decomposition, and service mesh patterns. Proven expertise in robust API design (REST, GraphQL, etc.), security, scalability, and maintainability.- Cloud-Native Stack : Expertise in cloud-native architecture (AWS/Azure), containerization (Docker/K8S), and infrastructure as code (IaC).- GenAI Integration : Experience integrating LLM APIs (OpenAI, Anthropic, open-source models) into production, real-world applications.- Agentic Architecture : Mandatory experience with agentic frameworks like LangGraph, CrewAI, AutoGen, or developing custom orchestration logic.- Memory & RAG : Proven experience designing for context management, Retrieval-Augmented Generation (RAG), and structured long-term memory systems.- Data Layer : Familiarity with vector databases (e.g., Pinecone, FAISS, Weaviate) and managing the embedding lifecycle.Preferred Skills : - Strong technical understanding of LLM behaviour, limitations, and prompt dynamics in high-volume production systems.- Exposure to advanced prompt evaluation frameworks like LangSmith or developing custom LLM feedback loops.- Experience with internal tooling or SDK development for platformized GenAI components consumed by product teams.- Previous architectural work in complex, enterprise-grade SaaS products. (ref:hirist.tech)