21 Nov
|
Weekday AI
|
India
This role is for one of Weekday’s clients Salary range: Rs 2500000
- Rs 6000000 (ie INR 25
- 60 LPA) Min
Experience:
8+ years
Location:
Remote (India) JobType: full time Domain: Artificial Intelligence, Cloud Architecture, Generative AI Role Overview We are looking for an experienced and technically proficient AWS AI Architect to lead the architecture, design, and development of enterprise-grade Agentic AI solutions. The role focuses on building secure, scalable, and production-ready AI systems that enable business users to interact with complex enterprise data platforms through natural language and receive accurate, explainable, and validated insights. The ideal candidate will have strong hands-on expertise in AWS-native AI services, particularly Amazon Bedrock, Agentic AI frameworks, Knowledge Graphs, semantic layers, and Text-to-SQL solutions. This is a hands-on architecture and engineering leadership role requiring deep SQL expertise, strong Python development skills, and practical experience in enterprise AI solution development. The candidate will be responsible for evolving existing proof-of-concept solutions into production-ready systems, making key architectural decisions, developing critical components, establishing quality and evaluation frameworks, and leading distributed data and GenAI engineering teams. Requirements
Key Responsibilities
1. Agentic AI Architecture & Development
- Design, develop, and enhance enterprise-grade Agentic AI architectures using Amazon Bedrock AgentCore and Strands Agents.
- Build scalable, secure, and reliable AI agent workflows capable of handling complex enterprise business queries.
- Integrate foundation models, Knowledge Bases, and Guardrails into enterprise AI applications.
- Establish robust agent execution, validation,
and control mechanisms to improve response accuracy and reliability. 2. Semantic Layer Development
- Design and implement governed semantic layers and business facts libraries.
- Define business metrics, reusable entities, data relationships, join conditions, data grain, and aggregation logic.
- Collaborate with business stakeholders and subject-matter experts to validate business definitions and ensure consistency.
- Establish reusable semantic models to support accurate and context-aware data retrieval. 3. Ontology & Knowledge Graph Engineering
- Design and implement enterprise ontologies and knowledge graphs using Amazon Neptune.
- Enable identity-based retrieval, relationship discovery, and contextual enrichment through business metadata.
- Work with graph technologies and query languages such as RDF, SPARQL, Gremlin, and openCypher.
- Integrate knowledge graphs with Agentic AI workflows and semantic retrieval systems. 4. Text-to-SQL Development & Optimization
- Develop deterministic Text-to-SQL solutions that translate natural-language business questions into accurate and validated SQL queries.
- Design intent-to-SQL compilation workflows with appropriate query validation and business logic controls.
- Ensure correctness of join paths, aggregations, data grain, and business metric definitions.
- Optimize SQL generation and execution across multiple enterprise data platforms.
- Build mechanisms to validate generated queries before execution.
5. Agent Orchestration & Workflow Engineering
- Integrate semantic layers, knowledge graphs, and SQL compilers into agent orchestration workflows.
- Develop and implement AI agent workflows using Strands Agents, LangGraph, CrewAI, or comparable frameworks.
- Establish probing, reasoning, validation, and error-handling mechanisms beyond basic prompt engineering.
- Ensure consistent execution and reliable outcomes across complex multi-step AI workflows. 6. Evaluation, Testing & Quality Assurance
- Develop comprehensive evaluation frameworks for LLM-based applications and Agentic AI systems.
- Create golden datasets, test harnesses, accuracy metrics, and automated validation processes.
- Evaluate AI-generated responses and SQL outputs for correctness, consistency, and reliability.
- Establish quality benchmarks and continuously improve system performance. 7. AWS Backend Engineering & Infrastructure
- Design and configure production-oriented backend architectures using AWS services.
- Implement DynamoDB for chat session management and Amazon RDS for agent context and metadata.
- Work with AWS Lambda, IAM, CloudWatch, and other relevant cloud services.
- Implement secure access controls, monitoring, logging, and enterprise-grade deployment practices.
- Ensure scalability, performance, security, and reliability of AI applications. 8. Technical Leadership & Stakeholder Collaboration
- Lead and mentor offshore data engineering and GenAI development teams.
- Drive technical implementation, architecture decisions, and engineering best practices.
- Collaborate with business stakeholders and subject-matter experts to translate requirements into technical solutions.
- Review code, oversee deve
📌 AWS AI Architect (India)
🏢 Weekday AI
📍 India