AI Solution Architect

Akaasa Technologies; United States; On-site; USD 150,000 - 210,000; Full time

Job summary

Diiiploy is seeking an AI Solution Architect to build and deploy AI agents for mid-market enterprise clients within AWS, Azure, and Google Cloud. You will stand up containerized environments, configure connections and MCPs, write prompts, and QA-tune before production.

You will handle full-stack development tasks, integrate LLM APIs, manage containers, and design scalable data flows. The role emphasizes collaboration with Trevor on architecture and requires strong communication and hands-on

Qualifications

• LinkedIn Page is required.
• Experience with multiple cloud platforms (AWS, Azure, Google Cloud).
• Background in enterprise/B2B environments with understanding of security constraints, access request delays, sandbox vs. production.
• Familiarity with agent frameworks (LangChain, CrewAI, Claude Code agents, or custom).
• Strong communication skills.

Responsibilities

• 1. Agent Builds (Primary): Spin up containers (sandboxed environments) for AI agents; Configure MCP connections, API integrations, and data connectors; Write and refine agent prompts based on PRD specifications; Connect agents to client data sources (databases, CRMs, email, cloud storage); Run 7-day minimum QA tuning periods; Deploy agents to production and monitor post-launch; Debug and resolve post-production issues.

Skills

Multi-cloud platforms

Enterprise/B2B experience

Agent frameworks

Communication

Docker

Tools

Docker

Job description

AI Solution Architect - Citizen Only

Client: Diiiploy

Note :: need Born Citizen

Must have:

• Experience with multiple cloud platforms (not just one)- AWS, Azure, Google Cloud
• Background in enterprise/B2B environments (understands security constraints, access request delays, sandbox vs. production)
• Familiarity with agent frameworks (LangChain, CrewAI, Claude Code agents, or custom)
• Strong communication
  • US Natural Citizen considered first and among all candidates.
• LinkedIn Page

This person builds and deploys AI agents for mid-market enterprise clients. They work within cloud infrastructure (AWS, Azure, Google Cloud), stand up containerized agent environments, configure connections and MCPs, write agent prompts, and run QA tuning before production launch. They don't design architecture from scratch - Trevor handles that - but they need to understand architecture well enough to implement it and troubleshoot independently

Description:

• Full-stack development - can build a functional web UI with a database backend (not just scripts). Needs to handle front-end and back-end independently
• AI/LLM integration - experience connecting to LLM APIs (Anthropic, OpenAI, Bedrock, Vertex). Understands prompting, token management, and agent architectures
• Containerization - Docker or equivalent. Comfortable spinning up, configuring, and managing containerized applications
• AI-assisted development - actively uses Claude Code, Cursor, or similar AI coding tools. This is non‑negotiable - the team builds with AI
• Database proficiency - SQL databases, Supabase, or equivalent. Can design schemas, write queries, and configure connections
• API integration - REST APIs, authentication flows, webhook configuration, MCP server setup
• Git/GitHub - clean commit history, branching, PRs
• Cloud infrastructure experience - hands‑on with at least one of: AWS, Azure, Google Cloud. Comfortable interacting with servers, databases, networking, and security groups

Core Responsibilities

1. Agent Builds (Primary)

• Spin up containers (sandboxed environments) for AI agents
• Configure MCP connections, API integrations, and data connectors
• Write and refine agent prompts based on PRD specifications
• Connect agents to client data sources (databases, CRMs, email, cloud storage)
• Run 7-day minimum QA tuning periods - catch edge cases before production
• Deploy agents to production and monitor post‑launch
• Debug and resolve post‑production issues

2. Client Onboarding Support

• Determine client cloud platform and existing infrastructure
• Document required connections, data sources, and access permissions
• Submit and track API key / account access requests
• Test access grants to confirm correct permissions (read, read/write, admin)

3. Internal Tools & Maintenance

• Maintain and improve Gbrain (company knowledge base)
• Support Distill (AI news briefing tool)
• Contribute to internal playbook and wiki documentation
• Evaluate new tools and frameworks during allocated R&D time