Capability Area

• Agentic AI

  • Required Skills: AWS AgentCore, Amazon Bedrock, multi-agent workflows, tool calling, memory, orchestration, RAG, prompt engineering
  • Expected Outcome: Build enterprise-grade AI agents that can reason, act, retrieve knowledge and integrate with business systems.

• Engineering

  • Required Skills: Advanced Python, TypeScript, REST APIs, serverless development, reusable frameworks, secure coding practices
  • Expected Outcome: Deliver scalable backend services and reusable accelerators for AI workloads.

• AWS Platform

  • Required Skills: Lambda, API Gateway, Step Functions, EventBridge, DynamoDB, S3, SQS/SNS, IAM, CloudWatch
  • Expected Outcome: Deploy secure, event-driven and resilient AI-powered applications on AWS.

• AIOps / LLMOps

  • Required Skills: Production monitoring, model/agent telemetry, latency, cost, hallucination tracking, prompt evaluation, incident management
  • Expected Outcome: Operate AI agents in production with observability, governance and continuous improvement.

• DevOps

  • Required Skills: CI/CD, Terraform/CDK/CloudFormation, GitHub/GitLab, Docker, release automation
  • Expected Outcome: Automate deployment, environment management and release governance.

Key Responsibilities

AI Agent Development

• Design and develop AI agents and multi-agent workflows using AWS AgentCore and Amazon Bedrock.
• Build autonomous and intelligent agents leveraging foundation models, tools, memory and orchestration capabilities.
• Implement RAG, tool calling, agent collaboration patterns and workflow automation for enterprise use cases.
• Integrate AI agents with enterprise APIs, databases, event streams and third-party platforms.
• Design secure and scalable AI architectures aligned to AWS Well-Architected principles.

Application Engineering

• Develop backend services, APIs and orchestration components using Python and TypeScript.
• Build event-driven and serverless applications using AWS Lambda, API Gateway, EventBridge, Step Functions, DynamoDB and SQS/SNS.
• Create reusable libraries, patterns and accelerators to standardize AI agent development across teams.

AIOps, Production Monitoring & Operations

• Establish monitoring, observability and operational governance for production AI workloads.
• Track agent performance, model latency, cost, prompt effectiveness, error rates and quality signals.
• Define alerting, incident response, RCA processes and production runbooks for AI applications.
• Troubleshoot AI agent issues across orchestration logic, integration failures, prompt/model behavior and platform dependencies.
• Continuously optimize reliability, accuracy, latency and cost for production GenAI systems.

DevOps & Platform Collaboration

• Build and maintain CI/CD pipelines for AI application and agent deployments.
• Implement Infrastructure as Code using Terraform, AWS CDK or CloudFormation.
• Collaborate with solution architects, platform teams, security teams and business stakeholders to deliver enterprise-grade AI solutions.

Required Skills & Qualifications

• Strong hands-on experience in Amazon Bedrock and agentic AI implementation patterns.
• Practical experience with AWS AgentCore or similar AI agent runtime/orchestration capabilities.
• Advanced Python and TypeScript development experience.
• Experience implementing RAG, prompt engineering, tool/function calling and AI workflow orchestration.
• Experience with production monitoring, observability and operational support for AI/ML or GenAI workloads.
• Strong understanding of AWS serverless, event-driven architecture, IAM and cloud security principles.
• Good understanding of CI/CD, Infrastructure as Code and release automation.
• Strong problem-solving, communication and stakeholder collaboration skills.

Preferred Skills

• Experience with LangChain, LangGraph, Semantic Kernel, CrewAI or similar agent frameworks.
• Experience with Bedrock Knowledge Bases, vector databases such as OpenSearch, Pinecone or Weaviate, and embedding-based retrieval patterns.
• Experience with MCP (Model Context Protocol), enterprise tool integration and workflow automation.
• Knowledge of AI safety, guardrails, governance, responsible AI and GenAI FinOps.
• Experience integrating AI solutions with ServiceNow, Salesforce, SAP or other enterprise systems.
• Experience operating highly available AI applications in production environments.

Certifications

• AWS Certified AI Practitioner – preferred.
• AWS Certified Machine Learning Engineer – preferred.
• AWS Certified Developer Associate – preferred.
• AWS Certified Solutions Architect Associate or Professional – preferred.

This is a high-priority role, and profiles are being reviewed immediately. If you’re interested, please share your resume at dilwar.h@i-q.co