About the Role :

We are seeking an experienced Senior Architect with strong expertise in Python, Generative AI, Agentic AI, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). The role will be responsible for translating business and technical requirements into scalable AI architectures and leading the design and implementation of production-grade AI solutions.

Key Responsibilities :

- Design and architect scalable AI solutions using Generative AI, LLMs, RAG, and Agentic AI technologies.

- Define technical architecture for LLM-powered applications, AI services, RAG pipelines, and intelligent automation solutions.

- Lead the design and development of agentic AI systems capable of executing multi-step workflows, using tools, APIs, and contextual information.

- Provide technical leadership to AI/ML engineering teams and guide them on architecture, design patterns, coding standards, and best practices.

- Develop and optimize Python-based AI applications, services, and AI/ML pipelines.

- Design RAG architectures covering document ingestion, chunking, embeddings, retrieval, reranking, context management, and LLM response generation.

- Define appropriate approaches for vector databases, semantic search, embeddings, and knowledge retrieval.

- Evaluate and select appropriate LLMs, AI frameworks, libraries, and supporting technologies based on business and technical requirements.

- Establish effective prompt engineering strategies and guide teams on prompt optimization, context engineering, and LLM evaluation.

- Drive model evaluation, fine-tuning, optimization, and experimentation to improve accuracy, relevance, reliability, and performance.

- Design APIs and integration patterns for embedding AI capabilities into enterprise applications and existing technology ecosystems.

- Identify and resolve architectural, performance, scalability, latency, reliability, and model-quality challenges.

- Conduct architecture reviews, code reviews, technical assessments, and design discussions across AI initiatives.

- Collaborate with product managers, data scientists, software engineers, and business stakeholders to translate requirements into technical solutions.

- Establish best practices for productionizing, monitoring, maintaining, and scaling AI applications.

- Stay updated with emerging developments in LLMs, Agentic AI, RAG, AI frameworks, and Generative AI engineering practices.

Required Skills & Qualifications :

- 10 - 15 years of overall experience in software engineering, AI/ML engineering, architecture, or related technology roles.

- Strong proficiency in Python and experience building scalable, production-grade applications.

- Strong hands-on experience with Generative AI, LLMs, Agentic AI, and LLM-based architectures.

- Strong expertise in Retrieval-Augmented Generation (RAG), embeddings, semantic search, and vector databases.

- Strong understanding of prompt engineering, context engineering, fine-tuning, and model evaluation.

- Experience with PyTorch, TensorFlow, or equivalent AI/ML frameworks.

- Strong understanding of LLM architecture, inference, tokenization, embeddings, model limitations, and performance considerations.

- Experience designing scalable AI application architectures and production AI solutions.

- Experience with modern AI/GenAI frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent.

- Strong understanding of API design, system integration, scalability, performance optimization, and software engineering principles.

- Strong analytical and problem-solving capabilities.

- Excellent communication and stakeholder management skills.

Good to Have :

- Experience with cloud-based AI/ML platforms and services.

- Experience designing multi-agent systems and complex AI orchestration workflows.

- Knowledge of AI application observability, monitoring, security, and governance.

- Experience with CI/CD, containers, and production deployment practices.

Key Deliverables :

- Scalable and production-ready AI/Generative AI architectures.

- Enterprise-grade LLM, RAG, and Agentic AI solutions.

- Technical standards and reusable architecture patterns for AI engineering.

- Improved model accuracy, application performance, scalability, and reliability.

- Effective technical guidance and mentoring for AI engineering teams.