AI / Agent Platform Engineer

SIDRAM TECHNOLOGIES; New York (NY); Hybrid; USD 190,000 - 240,000; Full time

Job summary

SIDRAM TECHNOLOGIES is seeking a Senior AI / Agent Platform Engineer in New York, NY. The role focuses on building scalable runtime services and distributed systems to power enterprise AI agent capabilities in production environments.

The candidate will design and implement long-running workflows, routing models, and multi-LLM integrations while collaborating with security and platform teams. Hybrid onsite schedule applies, with high demand for senior leadership and PMP-certified professionals.

Qualifications

• 15+ years of Software Engineering experience required.
• Strong distributed systems and system design background.
• Production experience with LLMs, AI agents, function calling and workflow orchestration.
• Runtime services for long-running and asynchronous AI workloads.
• Model routing and LLM abstraction layers.
• Multi-LLM provider integration.
• Tool invocation and execution state management.
• Retries, checkpointing and failure recovery.

Skills

15+ years

Distributed Systems

LLMs & Agents

Async AI workloads

Model Routing

Observability

Cloud-Native

Security & Identity

Tools

Kubernetes

Containers

APIs & SDKs

Job description

NOW HIRING: SENIOR AI / AGENT PLATFORM ENGINEER

Position: Senior AI / Agent Platform Engineer

Location: New York, NY

Employment: FULL-TIME ONLY

Work Model: Hybrid 3 Days Onsite

Experience: 15+ YEARS REQUIRED

Visa: INDEPENDENT VISA ONLY

Role Overview

Seeking a Senior AI / Agent Platform Engineer to build the execution layer powering enterprise AI agent capabilities.

The role focuses on designing scalable runtime services and distributed systems supporting long-running AI workflows in secure production environments.

Must-have Skills

• 15+ years of Software Engineering experience
• Strong Distributed Systems & System Design background
• Production experience with LLMs, AI Agents, Function Calling & Workflow Orchestration
• Runtime services for long-running & asynchronous AI workloads
• Model Routing & LLM Abstraction Layers
• Multi-LLM Provider Integration
• Tool Invocation & Execution State Management
• Retries, Checkpointing & Failure Recovery
• APIs & SDKs for reusable AI workflows
• Tracing, Telemetry & AI Evaluation
• Model APIs, Structured Outputs & Prompt/Context Management
• AI Performance Optimization
• Asynchronous Systems, Queues & State Management
• Strong Observability experience
• Cloud-Native Development
• Containers, Kubernetes, APIs & Microservices
• Experience collaborating with Security, Identity & Platform Engineering
• Active PMP Certification