Architect IAM for AI / Platform (PAM-Focused)

TekWissen•New York City, NY
•Onsite

About The Position

This is a hands-on engineering leadership role focused on AI platforms, LLM systems, and orchestration, with strong IAM/PAM alignment. The role involves leading hands-on development of AI-enabled and LLM-based applications, building agentic and multi-agent systems, and designing/implementing orchestration architectures. The position also requires owning full-stack AI system architecture, embedding secure-by-design principles, and driving reviews, mentoring, and best practices for AI engineering.

Requirements

  • Hands-on platform engineering experience end-to-end
  • Deep expertise in LLMs and model lifecycle
  • Deep expertise in prompt engineering and grounding
  • Deep expertise in hallucination mitigation
  • Strong system design experience including multi-agent architectures, distributed systems, and cloud-native development
  • Proficiency with C programming language
  • Proficiency with Unix/Linux systems
  • Knowledge of cryptography
  • Knowledge of authentication & authorization concepts
  • Experience working in secured enterprise environments
  • Experience working in Agile development teams
  • Python and Perl development skills
  • Ability to communicate technical concepts to business stakeholders
  • Strong collaboration and independent execution capabilities

Nice To Haves

  • Contributions to Linux/Unix/open-source projects are valued
  • Knowledge of Kerberos is preferred

Responsibilities

  • Lead hands-on development of AI-enabled and LLM-based applications
  • Build agentic and multi-agent systems
  • Design and implement orchestration architectures including function invocation, state and memory management, and policy-aware execution
  • Develop intelligent agent workflows using prompt design, grounding strategies, and tool orchestration layers
  • Own full-stack AI system architecture: APIs, data pipelines, model serving and observability
  • Ensure performance, scalability, and reliability across environments
  • Embed secure-by-design principles, including access controls, logging and traceability, explainability, and human-in-the-loop safeguards
  • Drive reviews, mentoring, and best practices for AI engineering
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service