- Key Accountabilities
- Define the technical architecture and solution blueprint for AI-powered agents, copilots, and intelligent automation solutions across enterprise products and platforms.

- Lead the design of scalable, secure, reusable, and enterprise-grade AI solutions that can be implemented by the AI Engineering team.

- Establish architecture principles, design standards, reference patterns, and technical guardrails for AI applications and agentic systems.

- Architect end-to-end AI solutions involving Large Language Models, retrieval-augmented generation, vector search, orchestration frameworks, enterprise APIs, workflow integration, and enterprise knowledge systems.

- Work closely with product teams, business stakeholders, and engineering leadership to translate business requirements and product goals into robust technical architectures and implementation approaches.

- Design architecture for AI agents supporting use cases such as intelligent assistants, recommendation engines, knowledge copilots, workflow automation, reporting intelligence, troubleshooting support, and decision-support applications.

- Define solution patterns for prompt orchestration, memory design, context management, tool invocation, grounding, output validation, and observability.

- Architect retrieval and knowledge access frameworks using enterprise documentation, support content, business knowledge repositories, operational data, and other structured and unstructured information sources.

- Drive decisions on model access strategy, abstraction layers, vector storage, orchestration engines, caching approaches, and integration standards.

- Review detailed technical designs prepared by engineers and provide architectural guidance to ensure alignment with defined standards and long-term technology direction.

- Partner with platform, security, DevOps, QA, and enterprise architecture teams to ensure that AI solutions are production-ready, supportable, secure, and aligned with organizational standards.





- Define non-functional architecture requirements for AI solutions including scalability, reliability, latency, resilience, cost efficiency, privacy, security, and governance.

- Guide the team on AI engineering best practices, reusable frameworks, and architectural decisions without taking on line management responsibility.

- Evaluate current AI technologies, frameworks, and tools, and recommend adoption based on business fit, enterprise readiness, and architectural value.

- Contribute to the long-term AI technology roadmap in collaboration with engineering leadership, product teams, and enterprise architecture stakeholders.

- Mandatory Skills
- Bachelor’s degree in Computer Science, Information Technology, Artificial Intelligence, Data Science, Engineering, or a related field.

- Minimum of 10 years of experience in software engineering and architecture, with at least 3 to 5 years of relevant experience in AI/ML, Generative AI, or enterprise AI solution architecture.

- Strong experience in designing enterprise-scale software architecture and distributed systems.

- Strong programming knowledge in Python and solid understanding of backend systems, APIs, integration patterns, and production-grade application design.

- Hands-on experience with Large Language Models, Generative AI platforms, prompt engineering, embeddings, semantic search, vector databases, and retrieval-augmented generation.

- Proven experience in architecting AI assistants, copilots, chatbots, or agent-based enterprise solutions.

- Strong understanding of microservices, event-driven architecture, backend integration patterns, and enterprise application connectivity.





- Ability to define architecture standards, reusable design patterns, and technical frameworks for engineering teams.

- Strong understanding of AI evaluation, output validation, grounding techniques, hallucination reduction, and observability practices.

- Good understanding of enterprise security, privacy, auditability, access control, and governance requirements for AI-enabled systems.

- Experience with AWS, Azure, or GCP and architecture for scalable, cloud-native enterprise applications.

- Familiarity with containerization, CI/CD, monitoring, logging, and production architecture practices.

- Strong architectural thinking, analytical ability, and problem-solving capability.

- Good communication and collaboration skills, with the ability to influence engineers, architects, product managers, and technical stakeholders.

- Experience working in Agile and modern product engineering environments.

- Desirable Skills
- Experience in enterprise software, SaaS platforms, customer engagement products, analytics platforms, digital transformation initiatives, or workflow automation solutions.

- Familiarity with AI orchestration and agent development frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, or similar tools.

- Exposure to Java, Spring Boot, Node.js, Kafka, workflow engines, rules engines, and microservices-based enterprise platforms.

- Experience with vector stores, caching layers, AI observability tools, and LLMOps platforms.

- Understanding of recommendation systems, personalization, analytics platforms, and decision-support systems.

- Familiarity with enterprise AI governance, responsible AI, and compliance-related architectural considerations.

- Experience mentoring engineers and guiding technical design reviews without direct people management responsibility.

- Understanding of enterprise platformization and reusable AI foundation architecture.

📌 Architect (Gurugram)
🏢 Comviva
📍 Gurugram