logo

Cloud202

AI Engineer

Department
Engineering
Job Type / Location
remote
Experience Required
3+ years
Posted On

About Us

Cloud202 Limited is a leading technology consulting company dedicated to helping businesses transform and innovate through cutting-edge technology solutions. We specialize in cloud migration, AI/ML, and application development, providing our clients with the expertise they need to stay ahead in a rapidly evolving digital landscape.

Position Overview

We are seeking an innovative AI Engineer to lead the development and implementation of enterprise-grade agentic AI solutions. This role requires deep expertise in the Gen-AI ecosystem, including Amazon Bedrock, Amazon Bedrock AgentCore, SageMaker AI, and emerging AI agent frameworks. The ideal candidate will drive enterprise AI transformation initiatives and build next-generation intelligent applications using cutting-edge agentic platforms and protocols.

Required Qualifications

Experience

  • Minimum 3+ years of hands-on experience with AWS cloud services and machine learning infrastructure
  • 2+ years of specific experience with generative AI, large language models (LLMs), and foundation models
  • Proven track record of building and deploying production-scale AI/ML applications on AWS

Certifications

  • Preferred: AWS Certified AI Practitioner or AWS Machine Learning Specialty

Core Technical Skills

Amazon Bedrock AgentCore Platform (Critical)

  • AgentCore Runtime: Deploy and operate AI agents securely at scale with serverless infrastructure, session isolation, and support for 8-hour execution windows
  • AgentCore Memory: Implement intelligent session and long-term memory with episodic learning capabilities for context-aware agent interactions
  • AgentCore Gateway: Build secure, centralized access to tools and APIs with minimal code transformation
  • AgentCore Identity: Implement seamless agent authentication across AWS services and third-party applications (Slack, Zoom, GitHub, Salesforce) using OAuth, Okta, Entra, or Amazon Cognito
  • AgentCore Tools: Utilize Code Interpreter for secure code execution and Browser Tool for enterprise-grade web automation within managed sandbox environments
  • AgentCore Observability: Implement end-to-end tracing, debugging, and monitoring through unified CloudWatch dashboards with OTEL compatibility
  • AgentCore Policy: Set fine-grained boundaries on agent actions with real-time deterministic controls
  • AgentCore Evaluations: Continuously assess agent quality and behavior for production readiness

Gen-AI Services & Foundation Models

  • Amazon Bedrock: Comprehensive experience with foundation model access, fine-tuning, and deployment
  • SageMaker AI: Model hosting, endpoints, auto-scaling, A/B testing, and deployment pipelines
  • Amazon Q Developer: AI-powered development automation and code transformation capabilities
  • Foundation Models: Hands-on experience with Claude (Anthropic), Llama (Meta), GPT models (OpenAI), Mistral, and Amazon Nova models

AI Agents Development & Frameworks

  • Strands Agents SDK: Build production-ready AI agents with model-driven approach, supporting single agents, multi-agent systems, and swarm architectures
  • Framework Expertise: Experience with CrewAI, LangGraph, LlamaIndex, Google ADK, OpenAI Agents SDK, or custom agent frameworks
  • Multi-Agent Orchestration: Design complex workflows with hierarchical delegation, agent-as-tools patterns, and dynamic capability discovery
  • Agentic Workflows: Build autonomous agents that reason, plan, use tools, and maintain context across long-running tasks
  • Tool Integration: Develop custom tools using Python decorators and integrate external APIs and services

Agent Protocols & Interoperability (Essential)

  • Model Context Protocol (MCP): Implement MCP servers and clients to provide standardized context and tool access to AI agents. Deploy MCP servers in AgentCore Runtime with OAuth authentication
  • Agent-to-Agent (A2A) Protocol: Build inter-agent communication systems using A2A protocol for peer-to-peer agent collaboration, capability negotiation, and task coordination
  • Agent Discovery: Implement agent cards and capability manifests for dynamic agent discovery and routing
  • Protocol Integration: Deploy agents supporting both MCP and A2A protocols for maximum interoperability across enterprise systems

Advanced Technical Skills

  • Vector Databases: Amazon OpenSearch, Pinecone, or similar for RAG implementations
  • Programming: Expert-level Python and JavaScript/TypeScript, with focus on AI/ML libraries and async programming
  • APIs & Integration: RESTful APIs, GraphQL, JSON-RPC 2.0, Server-Sent Events (SSE), real-time streaming, webhook integration
  • Prompt Engineering: Advanced prompt flows, few-shot learning, chain-of-thought reasoning, and structured output generation
  • Knowledge Bases: RAG implementation with enterprise data integration and semantic search
  • Guardrails & Safety: Bedrock Guardrails, content filtering, bias detection, and responsible AI practices
  • Custom Model Fine-tuning: Adapting foundation models for domain-specific use cases

Advanced GenAI Applications

  • Retrieval-Augmented Generation (RAG): Enterprise search, document Q&A, knowledge management
  • Content Generation: Text, image, code, and multimedia content creation
  • Conversational AI: Chatbots, virtual assistants, customer service automation with memory retention
  • Code Generation & Analysis: Automated code review, documentation, refactoring, and software modernization
  • Data Analysis & Insights: Natural language to SQL, automated reporting, business intelligence

Key Responsibilities

Solution Architecture & Design

  • Design end-to-end generative AI solutions using Amazon Bedrock AgentCore as the primary agentic platform
  • Architect scalable, cost-effective AI pipelines leveraging AgentCore Runtime for serverless deployment
  • Implement MCP and A2A protocols for agent interoperability and tool integration
  • Design multi-agent architectures with proper orchestration, memory management, and observability
  • Create technical documentation and best practices for AgentCore implementations

Development & Implementation

  • Build production-ready agentic applications using Amazon Bedrock AgentCore services (Runtime, Memory, Gateway, Identity, Observability)
  • Develop AI agents using Strands Agents SDK and other framework-agnostic approaches
  • Implement MCP servers for tool and data access across enterprise systems
  • Deploy A2A-compliant agents for cross-platform agent collaboration
  • Implement RAG systems with vector databases and AgentCore Gateway for secure data access
  • Create automated workflows for model deployment, monitoring, and evaluation
  • Integrate AI capabilities into existing enterprise applications with proper authentication and governance

Model & Agent Management

  • Evaluate and select appropriate foundation models for specific use cases
  • Implement AgentCore Policy for fine-grained control over agent actions and permissions
  • Use AgentCore Evaluations for continuous quality assessment and optimization
  • Optimize agent performance, cost, and latency using AgentCore Observability insights
  • Ensure compliance with data privacy, security requirements, and responsible AI practices

Innovation & Research

  • Stay current with latest AWS AI service releases, AgentCore capabilities, and agentic AI protocols
  • Experiment with emerging AI techniques, multi-agent patterns, and protocol enhancements
  • Prototype new use cases and proof-of-concepts using AgentCore platform

View Assessment Process

Think you'll be a good fit?