Description

Job Description

We are looking for an experienced Senior AI System Architect to design scalable, secure, and production-grade AI-powered platforms from the ground up. This role goes beyond traditional cloud architecture and requires expertise in modern AI system design, including Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Agentic AI workflows, and Vector Search infrastructure.

The ideal candidate will be responsible for architecting enterprise-grade AI-powered applications, making end-to-end architectural decisions across application, AI inference, data, cloud infrastructure, integrations, and operational reliability while guiding engineering teams through implementation and best practices.

Key Responsibilities

• Design and architect end-to-end AI-powered platforms, including LLM inference pipelines, RAG architectures, multi-agent orchestration, and conversational AI solutions.
• Build scalable vector search and knowledge management architectures using vector databases such as OpenSearch, Pinecone, Weaviate, or pgvector.
• Define LLM serving strategies including model routing, prompt optimization, response streaming, fallback mechanisms, token management, and latency optimization.
• Architect cloud-native solutions on AWS using services including EC2, ECS/EKS, Lambda, S3, RDS, DynamoDB, API Gateway, SQS/SNS, Amazon Bedrock, SageMaker, CloudWatch, IAM, and VPC.
• Own architecture across application, infrastructure, integration, deployment, and data layers.
• Prepare architecture documents, technical design specifications, trade-off analyses, and technology roadmaps.
• Define standards for microservices, CI/CD pipelines, observability, resiliency, disaster recovery, and AI governance.
• Implement AI security best practices including prompt injection prevention, PII handling, content filtering, guardrails, and audit logging.
• Evaluate technologies based on scalability, performance, security, cost optimization, and maintainability.
• Guide engineering teams through implementation, architecture reviews, and troubleshooting of complex production issues.
• Collaborate with Product, DevOps, Security, and Business stakeholders to translate business requirements into scalable technical solutions.
• Communicate architectural decisions effectively with both technical and non-technical stakeholders.

Required Skills

• 8+ years of software development or solution architecture experience.
• Minimum 5+ years of hands-on Python development experience.
• Minimum 3+ years of experience designing and implementing AI/Generative AI solutions.
• Strong experience designing production-grade GenAI systems, including RAG pipelines, LLM orchestration, Agentic AI workflows, and vector search architectures.
• Hands-on experience with AWS services including Amazon Bedrock, SageMaker, Lambda, ECS/EKS, EC2, S3, API Gateway, RDS, DynamoDB, IAM, CloudWatch, and VPC.
• Strong understanding of distributed systems, microservices architecture, REST/gRPC APIs, and event-driven architecture.
• Experience with Kubernetes, Docker, CI/CD pipelines, and Infrastructure as Code using Terraform or CloudFormation.
• Experience working with vector databases such as Pinecone, Weaviate, OpenSearch, FAISS, or pgvector.
• Good understanding of LLM infrastructure including streaming, batching, context management, prompt engineering, and cost optimization.
• Knowledge of AI security, governance, prompt injection prevention, content moderation, compliance logging, and PII protection.
• Strong knowledge of SQL, NoSQL databases, cloud security, encryption, IAM, secrets management, and production monitoring.
• Excellent analytical, problem-solving, communication, and stakeholder management skills.

Preferred Skills

• Experience with LangChain, LangGraph, LlamaIndex, or similar AI orchestration frameworks.
• Experience building enterprise AI platforms and conversational AI solutions.
• Familiarity with AI observability, monitoring, and model performance optimization.
• Experience with cloud migration and modernization initiatives.
• AWS Certification or AI/ML certifications will be an added advantage

Key Skills

Education

Any Graduate