AI/ML Engineer: LLM Security & Prompt Engineering

Triunity Software, Inc.; México; On-site; MXN 580,000 - 900,000; Full time

Job summary

Triunity Software, Inc. is seeking an AI/ML Engineer with 3–6 years of hands-on experience in Generative AI, LLMs, prompt engineering, and AI security. You will build and secure LLM-powered applications with a focus on prompt-injection detection and red-teaming.

You will develop RAG pipelines, embeddings, and vector search, design robust prompts, and implement guardrails. Collaboration with cloud platforms and production deployments is required.

Qualifications

• 3–6 years of experience in AI/ML or related field.
• Hands-on experience with Generative AI, LLMs, and prompt engineering.
• Experience building secure LLM-powered applications and evaluating AI security risks.

Responsibilities

• Develop AI/ML and LLM-based applications using Python.
• Build RAG pipelines, AI agents, embeddings, and vector-search solutions.
• Design and optimize prompts and LLM workflows.
• Identify and test prompt injection, jailbreaks, data leakage, and unauthorized tool usage.
• Develop guardrails and security controls for LLM applications.
• Perform LLM evaluation, adversarial testing, and security assessments.
• Work with cloud platforms, APIs, and production AI deployments.

Skills

LLMs & Generative AI

Prompt Engineering & LLM Evaluation

RAG, embeddings & vector databases

LangChain/LlamaIndex frameworks

AWS/Azure/GCP familiarity

OWASP LLM security concepts

Tools

Python

Job description

Triunity Software, Inc. is seeking an AI/ML Engineer with 3–6 years of hands-on experience in Generative AI, LLMs, prompt engineering, and AI security. You will build and secure LLM-powered applications with a focus on prompt-injection detection and red-teaming.

You will develop RAG pipelines, embeddings, and vector search, design robust prompts, and implement guardrails. Collaboration with cloud platforms and production deployments is required.