AI Engineer - Agentic Systems

vibehackers; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

vibehackers is seeking a hands-on AI Engineer to design, build, and deploy production-grade agentic AI systems for enterprise environments. You will own multi-agent orchestration, tool integration, and safety guardrails, working remotely across the US.

Leverage MCP, Claude Agent SDK, OpenAI Agents SDK, and Vertex AI tools to implement robust architectures, scalable microservices, and memory/context management with a strong emphasis on reliable production delivery.

Qualifications

• Hands-on experience building autonomous agent systems and tool-calling workflows into production.
• ],
• job_responsibilities_description [

Responsibilities

• Design and deploy autonomous and multi-agent orchestration workflows to execute complex, multi-step enterprise processes.
• Implement structured tool-use frameworks and integrate external APIs and services using protocols such as MCP.
• Engineer advanced prompt strategies, dynamic memory management, and memory layers to optimize model performance.
• Implement production-grade guardrails, schema enforcement, latency optimization, and defensive exception handling across agentic workflows.
• Deploy, scale, and maintain agentic microservices on cloud infrastructure using containerized and serverless platforms.

Skills

Multi-agent orchestration

Tool integration

Prompt engineering

Memory and context management

Safety guardrails

Distributed systems

Cloud architecture

API integrations

Tools

Anthropic Claude Agent SDK

OpenAI Agents SDK

GKE

Cloud Run

Pub/Sub

BigQuery

Vertex AI Agent Engine

Pydantic/JSON schemas

Job description

Explicitly focused on agentic AI and agent SDKs (MCP, Anthropic/OpenAI/Vertex), so it's about building and iterating on agent systems with frontier models.

About the Role

Hands-on AI Engineer to design, build, and deploy production-grade agentic AI systems for enterprise, focusing on multi-agent orchestration, tool integration, and robust safety guardrails. Fully remote within the US (East Coast time zone preferred) with minimal travel.

Job Description

Role

We are seeking a highly hands-on AI Engineer to design, build, and deploy production-grade agentic AI systems for enterprise environments. The role focuses on multi-agent orchestration, complex tool execution, dynamic context and memory management, and implementing production-grade safety guardrails.

Key Responsibilities

• Design and deploy autonomous and multi-agent orchestration workflows to execute complex, multi-step enterprise processes.
• Implement structured tool-use frameworks and integrate external APIs and services using protocols such as the Model Context Protocol (MCP).
• Engineer advanced prompt strategies, dynamic context management, and memory layers to optimize model performance and reasoning accuracy.
• Implement production-grade guardrails, schema enforcement, latency optimization, and defensive exception handling across agentic workflows.
• Deploy, scale, and maintain agentic microservices on cloud infrastructure using containerized and serverless platforms.

Requirements

• Demonstrated, hands-on experience building, testing, and shipping autonomous agent systems and tool-calling workflows into production.
• Strong proficiency in at least one major model ecosystem (Anthropic, OpenAI, or GCP Vertex AI) and related agent SDKs and protocols.
• Experience building and deploying distributed applications on Google Cloud Platform (GKE, Cloud Run, Pub/Sub, BigQuery).
• Solid software engineering foundations: software design patterns, API integrations, structured outputs (Pydantic/JSON schemas), and microservices architecture.

Tech & Tools (explicitly mentioned)

Anthropic (Claude Agent SDK, Model Context Protocol), OpenAI (OpenAI Agents SDK, Responses API, File Search), GCP Vertex AI (Gemini, Google ADK / Vertex AI Agent Engine), GKE, Cloud Run, Pub/Sub, BigQuery, Pydantic, JSON schemas, containerized and serverless platforms.

Location & Work Model

• Remote within the United States (East Coast time zone slightly preferred). Minimal travel required.
• Fully remote US-based role with high execution autonomy.

Engagement Highlights

• Ship enterprise-scale, production agent systems beyond proof-of-concept.
• Work directly with state-of-the-art agent SDKs, Model Context Protocol, and multi-model ecosystems across Anthropic, OpenAI, and GCP.

Anthropic Claude Agent SDK Model Context Protocol (MCP) OpenAI OpenAI Agents SDK Responses API File Search GCP Vertex AI Gemini Google ADK Vertex AI Agent Engine GKE Cloud Run Pub/Sub BigQuery Pydantic JSON Schema Containerization Serverless

Skills

Agentic AI Multi-agent orchestration Prompt engineering Safety and guardrails Cloud architecture Microservices API integration Scalability Performance optimization Exception handling Software design Testing and deployment Structured outputs Distributed systems Memory and context management