AI Solution Architect

Qualification: We are seeking a AI Solutions Architect with strong experience in designing and developing enterprise-grade AI platforms, RAG pipelines, multi-agent systems, and cloud-native AI solutions. The ideal candidate will be responsible for architecting scalable Generative AI and Agentic AI applications, developing intelligent agent workflows, implementing AI governance and security controls, and delivering production-ready AI solutions across cloud environments. This role requires a strong focus on AI architecture, agent orchestration, retrieval optimization, evaluation, observability, automation, and collaboration with cross-functional teams to deliver secure, scalable, reliable, and high-quality AI solutions. What You'll Bring 12-14 years of experience in software engineering, AI/ML engineering, data engineering, or related fields, with strong hands-on experience building enterprise AI solutions. Strong experience designing and developing Generative AI and Agentic AI applications using foundation models, RAG architectures, and agent-based workflows. Strong programming and application development experience using Python, FastAPI, and related frameworks. Experience designing high-performance RAG pipelines, vector search solutions, embedding workflows, semantic caching, and context-window optimization. Strong experience with multi-agent architectures, agent orchestration, memory management, autonomous planning, and stateful workflows. Strong understanding of AI evaluation, observability, hallucination reduction, responsible AI, data privacy, governance, and security. Ability to collaborate effectively with software engineers, data engineers, data scientists, architects, product teams, and business stakeholders. Experience designing scalable, production-ready AI platforms and reusable enterprise architecture patterns. Preferred Qualification Experience with LangChain, LangGraph, and Amazon Bedrock Runtime. Experience with Model Context Protocol (MCP) and Agent-to-Agent (A2A) interoperability standards. Experience with vector databases such as Milvus and Amazon Aurora PostgreSQL. Experience implementing CI/CD pipelines and DevOps practices for AI/ML applications. Experience with Docker, Kubernetes, and cloud-native application deployment. Knowledge of AI evaluation frameworks, tracing, observability, and monitoring of model and agent performance. Experience with AWS services including Amazon Bedrock, Lambda, EKS, SageMaker, S3, RDS, and DocumentDB. Knowledge of responsible AI practices including bias mitigation, model risk management, privacy, compliance, and AI safety guardrails. Experience optimizing AI applications for latency, scalability, reliability, cost, and token consumption. Skills Required: Generative AI, Agentic AI, RAG, Python Role: What You'll Do Design, develop, and maintain scalable Generative AI and Agentic AI platforms using cloud-native architectures. Design and implement high-performance Retrieval-Augmented Generation (RAG) pipelines, semantic search, embedding workflows, and vector database integrations. Develop agentic workflows supporting autonomous planning, reasoning, decision-making, tool use, and function calling. Design and implement multi-agent collaboration patterns including supervisor-worker, decentralized collaboration, and stateful graph architectures. Develop agent memory and state-management capabilities using frameworks such as LangChain, LangGraph, and Amazon Bedrock Runtime. Implement structured data extraction, schema-driven outputs, context optimization, and intelligent retrieval strategies. Integrate vector databases such as Milvus and Amazon Aurora PostgreSQL to support high-performance similarity search and retrieval. Build data and embedding pipelines using Python, FastAPI, Apache Spark, and related technologies. Develop and deploy AI applications using AWS services including Amazon Bedrock, Lambda, EKS, SageMaker, S3, RDS, and DocumentDB. Implement AI evaluation frameworks, tracing, observability, and monitoring to measure agent performance, latency, token usage, errors, and failure states. Develop guardrails to reduce hallucinations and improve the reliability, safety, and accuracy of AI-generated outputs. Implement governance, security, data privacy, compliance, bias mitigation, and responsible AI practices across AI platforms. Implement CI/CD pipelines and automated testing strategies for non-deterministic AI applications and model outputs. Containerize and orchestrate AI workloads using Docker and Kubernetes. Collaborate with cross-functional teams to define enterprise AI architectures, reusable design patterns, and production deployment strategies. Evaluate emerging Generative AI, Agentic AI, interoperability, and cloud technologies and recommend improvements to existing AI solutions. Experience: 12 to 14 years Job Reference Number: 14101