AWS Solution Architect (GenAI & Agentic AI)
Role details
Job location
Tech stack
Job description
We are seeking an experienced AWS Solution Architect with strong expertise in Generative AI (GenAI) and Agentic AI systems. The ideal candidate will be responsible for designing, developing, and deploying scalable AI-driven solutions on AWS, with a focus on autonomous agents, LLM-based applications, and intelligent workflows., Design and architect scalable, secure, and cost-efficient solutions on AWS Cloud Build and deploy Generative AI applications using large language models (LLMs) Develop and implement Agentic AI systems (autonomous agents capable of decision-making and task execution) Integrate AI/ML services such as Amazon Bedrock, SageMaker, Lambda, and API Gateway Collaborate with business stakeholders to translate requirements into technical solutions Lead architecture discussions, design reviews, and provide technical guidance Ensure best practices in cloud architecture, security, and compliance Optimize performance and cost of AI workloads on AWS Stay updated with emerging trends in AI, GenAI, and cloud technologies
Requirements
Bachelor s or Master s degree in Computer Science, Engineering, or related field 8+ years of experience in IT with 3+ years in AWS Solution Architecture Strong hands-on experience with AWS services (EC2, S3, Lambda, RDS, VPC, etc.) Experience with Generative AI frameworks (OpenAI, Bedrock, Hugging Face, etc.) Solid understanding of LLMs, prompt engineering, fine-tuning, and embeddings Experience building Agentic AI workflows (multi-agent systems, orchestration, tool usage) Proficiency in Python or similar programming languages Experience with microservices architecture and REST APIs Familiarity with DevOps practices (CI/CD, Docker, Kubernetes), AWS Certified Solutions Architect (Associate/Professional) Experience with LangChain, AutoGen, CrewAI, or similar agent frameworks Knowledge of vector databases (Pinecone, FAISS, etc.) Experience with RAG (Retrieval-Augmented Generation) architectures Exposure to MLOps and model deployment pipelines