AI Application Engineer

Role Name: AI Application Engineer
Location: Remote (California Consultants Only)
Job Type: Full Time
Interview Mode: Virtual
Pay Rate: Based on Experience

Job Description:

We are seeking a highly skilled AI Application Engineer to design, develop, and integrate enterprise-grade AI agent applications. The ideal candidate will have hands-on experience working with large language models (LLMs), agentic frameworks, and cloud-native technologies. This role requires strong Python and AWS engineering expertise to build production-ready, scalable, secure, observable, and reliable AI agents and enterprise tool integrations.

Key Responsibilities:

• Collaborate with cross-functional teams to define AI agent requirements, integration patterns, and implementation plans.
• Design and develop orchestration agents and domain-specific agents using Python 3.12, LangChain, LangGraph, or Strands.
• Integrate LLMs and foundation models for reasoning, structured responses, tool calling, and workflow execution.
• Deploy and operate AI agents using Amazon Bedrock AgentCore Runtime.
• Implement agent-to-agent communication using A2A 1.0 and the official Python a2a-sdk.
• Build secure agent-to-tool integrations using the Model Context Protocol (MCP) and Amazon Bedrock AgentCore Gateway.
• Use PostgreSQL for task persistence, workflow status, agent state, and idempotency management.
• Store and manage generated documents and artifacts using Amazon S3 and secure credentials with AWS Secrets Manager.
• Implement logging, metrics, and distributed tracing using AgentCore Observability, OpenTelemetry, and Amazon CloudWatch.
• Develop unit, integration, and A2A contract tests using pytest, and troubleshoot complex AI application issues.
• Document agent frameworks, integration patterns, development standards, and operational best practices.

Qualifications:

• Degree: Bachelor s or Master s degree in Computer Science, Engineering, or a related field.
• AI & LLM Integration: Proven experience developing AI applications and integrating LLMs or foundation models with enterprise systems.
• Python Engineering: Strong proficiency in Python 3.12+, asynchronous programming, API development, and object-oriented design.
• Agentic Frameworks: Hands-on experience with LangChain, LangGraph, or similar agentic AI frameworks.
• Prompt Engineering: Strong understanding of prompt engineering, tool calling, structured outputs, context management, and LLM response validation.
• Cloud & APIs: Experience with AWS services, relational databases, REST APIs, and cloud-native application development.
• Architecture: Familiarity with multi-agent orchestration, distributed systems, task persistence, and asynchronous workflows.
• Soft Skills: Strong problem-solving, debugging, communication, and collaboration skills.

Preferred Skills:

• AWS Bedrock Stack: Experience with Amazon Bedrock AgentCore Runtime, Gateway, and Observability.
• Protocols & MCP: Knowledge of A2A protocols, MCP clients and servers, and enterprise tool integration.
• Infrastructure & Tools: Experience with PostgreSQL, Amazon S3, AWS Secrets Manager, OpenTelemetry, CloudWatch, HashiCorp, and pytest.
• Production Deployment: Experience deploying secure, scalable, and highly available AI applications in production environments.
• DevOps & MLOps: Familiarity with Docker, Kubernetes, CI/CD pipelines, Retrieval-Augmented Generation (RAG), LLM evaluation, and AI guardrails.