AI Agent Platform Engineer

Intellisoft Technologies; New York (NY); On-site; USD 120,000 - 160,000; Full time

Job summary

Intellisoft Technologies is seeking a Senior AI / Agent Platform Engineer to design and build the execution layer powering enterprise AI agent capabilities. You will craft scalable runtime services and distributed systems to support long-running AI workflows in secure production environments.

Join a team focusing on model routing across providers, tool invocation, state management, retries, and observability, delivering reusable AI workflows with robust APIs and SDKs.

Qualifications

• Strong software engineering and distributed systems background.
• Experience building production AI applications using LLMs, AI Agents, Function Calling, or Workflow Orchestration.
• Experience with asynchronous systems, queues, state management, retries, and observability.
• Understanding of model APIs, structured outputs, prompt/context management, and AI performance optimization.

Responsibilities

• Design and build runtime services for long-running, asynchronous AI workloads.
• Develop model routing and abstraction layers across multiple LLM providers.
• Implement tool invocation, execution state management, retries, checkpointing, and failure recovery.
• Build APIs and SDKs enabling reusable AI workflows.
• Develop tracing, telemetry, and evaluation capabilities.
• Collaborate with Security, Identity, and Platform Engineering teams.

Skills

Software engineering

Distributed systems

LLMs / AI Agents

Function calling

Workflow orchestration

Asynchronous systems

Observability

Model APIs

Prompt / context management

Performance optimization

Job description

We are seeking a Senior AI / Agent Platform Engineer to build the execution layer powering enterprise AI agent capabilities. This role focuses on designing scalable runtime services and distributed systems that support long-running AI workflows in secure production environments.

Key Responsibilities

• Design and build runtime services for long-running, asynchronous AI workloads.
• Develop model routing and abstraction layers across multiple LLM providers.
• Implement tool invocation, execution state management, retries, checkpointing, and failure recovery.
• Build APIs and SDKs enabling reusable AI workflows.
• Develop tracing, telemetry, and evaluation capabilities.
• Collaborate with Security, Identity, and Platform Engineering teams.

Required Qualifications

• Strong software engineering and distributed systems background.
• Experience building production AI applications using LLMs, AI Agents, Function Calling, or Workflow Orchestration.
• Experience with asynchronous systems, queues, state management, retries, and observability.
• Understanding of model APIs, structured outputs, prompt/context management, and AI performance optimization.