Gen AI Platform Engineer

Vaiticka Solution; Roanoke (TX); On-site; USD 150,000 - 210,000; Full time

Job summary

Vaiticka Solution is seeking an experienced AI Platform Engineer to design and implement enterprise AI agent frameworks and orchestration platforms.

You will develop integrations with LLM services, enterprise AI APIs, and backend systems, and build secure tool invocation frameworks while enforcing prompt safety and governance.

Collaborating with product and security teams, you will deliver scalable, compliant Generative AI solutions across the business.

Qualifications

• 5+ years designing enterprise AI agent frameworks and orchestration platforms.
• Strong experience with Generative AI and Agentic AI frameworks.
• Hands-on with LangChain, LangGraph, Semantic Kernel, MCP.
• Proficiency in Python, Java, and API integrations.
• Experience with prompt engineering, governance, and AI safety.
• Knowledge of model orchestration and enterprise AI services integration.

Responsibilities

• Design and implement enterprise AI agent frameworks and orchestration platforms.
• Develop integrations with LLMs, enterprise AI services, APIs, and backend systems.
• Build tool invocation frameworks enabling secure interaction between AI agents and business applications.
• Implement prompt safety controls, policy enforcement, guardrails, and responsible AI practices.
• Develop telemetry and monitoring capabilities for AI usage, performance, and governance.
• Collaborate with product and security teams to deliver scalable and compliant Generative AI solutions.

Skills

Enterprise AI design

Generative AI & Agentic AI

LangChain

LangGraph

Semantic Kernel

MCP

Python

Java

API integrations

Prompt engineering

AI governance

Model orchestration

Cross-functional collaboration

Job description

We are seeking an experienced AI Platform Engineer to design and implement enterprise AI agent frameworks and orchestration platforms. The ideal candidate will have expertise in Generative AI, Agentic AI, LLM integrations, and AI governance, with the ability to build scalable, secure, and compliant AI solutions.

Key Responsibilities

• Design and implement enterprise AI agent frameworks and orchestration platforms.
• Develop integrations with LLMs, enterprise AI services, APIs, and backend systems.
• Build tool invocation frameworks that enable secure interaction between AI agents and business applications.
• Implement prompt safety controls, policy enforcement, guardrails, and responsible AI practices.
• Develop telemetry and monitoring capabilities for AI usage, performance, and governance.
• Collaborate with product and security teams to deliver scalable and compliant Generative AI solutions.

Required Skills

• 5+ years of experience designing and implementing enterprise AI agent frameworks and orchestration platforms.
• Strong experience with Generative AI and Agentic AI frameworks.
• Hands-on experience with LangChain, LangGraph, Semantic Kernel, and Model Context Protocol (MCP).
• Proficiency in Python, Java, and API integrations.
• Experience with prompt engineering and AI governance practices.
• Strong understanding of LLM integration and model orchestration.
• Experience integrating enterprise AI services, APIs, and backend systems.
• Knowledge of AI safety, policy enforcement, and responsible AI principles.
• Experience building monitoring, telemetry, and governance solutions for AI platforms.
• Strong collaboration skills with the ability to work effectively across product, engineering, and security teams.