Senior AI Platform Engineer

Intone Inc; New York, Northern (NY, KY); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Intone Inc. is seeking a Senior AI Platform Engineer for a 12-month contract based in New York City. You will design, build, and secure AI platform infrastructure in a regulated environment, bridging technical implementation with security and compliance requirements.

You will collaborate with InfoSec, Risk, and Compliance to implement IAM policies, guardrails, logging, and network protections, while deploying Gen AI apps and RAG architectures using AWS services.

Qualifications

• 6+ years of progressive engineering experience in AI/platforms or cloud platforms.
• Experience collaborating with InfoSec, Risk and Compliance to define and implement controls in regulated environments.
• Hands-on security controls through IAM policies, guardrails, logging and audit trails.
• Proficiency with Gen AI models (GPT, Claude, Gemini, LLaMA) and prompt engineering.
• Experience with agentic AI, MCP, and Graph/RAG architectures.
• Knowledge of Gen AI frameworks and LLM gateway/proxy patterns.
• Hands-on experience with AWS services including AgentCore, Bedrock, EC2, EKS, Lambda, Fargate, Glue.
• Familiarity with Terraform, Puppet, and Docker for IaC and tooling.
• Strong stakeholder management across security, risk, compliance, and engineering.

Responsibilities

• Design AI platform architecture on AWS and related services.
• Implement security controls with InfoSec, Risk and Compliance teams.
• Develop and deploy Gen AI apps using multiple models.
• Implement vector/graph DBs for RAG and knowledge graphs.
• Write IaC (Terraform, Puppet, Docker) for scalable deployments.
• Develop automation tools in Python for platforms and operations.
• Establish automated testing/evaluation for platform and AI behavior.
• Manage AWS costs and usage across platform services.
• Coordinate across security, risk, compliance, and engineering stakeholders.
• Contribute to DevSecOps and Agile processes.

Skills

Senior AI Platform Engineering

Team leadership

Gen AI platforms

AWS & cloud infrastructure

Security & compliance focus

DevSecOps & SDLC

Python automation

Infrastructure as Code

6+ years engineering

Tools

Terraform

Puppet

Docker

AWS services (EC2/ELB/Lambda/EKS)

Weaviate/Milvus/PGVector

Neo4j/Neptune

Job description

We are hiring a Senior AI Platform Engineer for a 12-month contract position based in New York City. This role focuses on designing, building, and securing AI platform infrastructure in a regulated environment, bridging technical implementation with security and compliance requirements.

Responsibilities

• Design and implement AI platform architecture on AWS, including agentic AI systems, LLM gateways, and supporting infrastructure (Bedrock, AgentCore, EKS, Lambda, and related services).
• Build and configure technical controls in collaboration with InfoSec, Risk, and Compliance teams, including IAM policies, guardrails, logging, audit trails, quota and rate limiting, and network and data-protection mechanisms.
• Develop and deploy Gen AI applications using models such as GPT, Claude, Gemini, and LLaMA, with proficiency in prompt engineering and agentic AI frameworks.
• Implement and optimize vector and graph database solutions (Weaviate, Milvus, PGVector, Neo4j, Neptune) for retrieval-augmented generation (RAG) and knowledge graph architectures.
• Write and maintain Infrastructure as Code (Terraform, Puppet, Docker) for reproducible, scalable deployments.
• Develop automation tools and platform services in Python (NumPy, Pandas, Boto3) to support engineering and operational workflows.
• Establish automated testing and evaluation frameworks (Ragas, Playwright, Selenium, Zephyr) to validate platform functionality and AI model behavior.
• Manage AWS costs, resource usage, and credit allocation across platform services.
• Coordinate across security, risk, compliance, and engineering stakeholders to align technical solutions with regulatory and operational requirements.
• Contribute to DevSecOps practices, SDLC best practices, and Agile Scrum/Kanban workflows.

Qualifications

• Required
  • 6+ years of progressive engineering experience, including 1–2+ years in AI platform, cloud platform, or emerging-technology enablement roles.
  • Demonstrated experience working with InfoSec, Risk, and Compliance teams to define, review, and implement technical controls in regulated environments.
  • Hands‑on experience implementing security controls through configuration and code: IAM and access policies, guardrails, logging and audit trails, quota and rate limiting, and network and data‑protection controls.
  • Proficiency with Gen AI models (GPT, Claude, Gemini, LLaMA) and prompt engineering techniques.
  • Experience with agentic AI, Model Context Protocol (MCP), and Graph/RAG architectures, including building and supporting agents, skills, and MCP servers.
  • Knowledge of Gen AI frameworks and LLM gateway/proxy patterns.
  • Hands‑on experience with AWS cloud services, including AgentCore, Bedrock, EC2, ELB/GLB/NLB, EKS, Fargate, Lambda, Athena, Glue, and Lake Formation, including cost management and usage/credit monitoring.
  • Experience with Infrastructure as Code tools: Terraform, Puppet, and Docker.
  • Python programming skills (NumPy, Pandas, Boto3) for automation, tooling, and platform services.
  • Experience with vector and graph databases (Weaviate, Milvus, PGVector, Neo4j, Neptune) and query optimization.
  • Familiarity with automated testing and evaluation frameworks (Ragas, Playwright, Selenium, Zephyr).
  • Knowledge of SDLC best practices, DevSecOps, Agile Scrum/Kanban, and work management tools (JIRA, Confluence, JIRA Align).
  • Strong stakeholder management skills and ability to broker agreements across security, risk, compliance, and engineering teams.