AI Prompt Engineer

Innova Solutions•Charlotte, NC

2h•Hybrid

About The Position

A client of Innova Solutions is immediately hiring for AI Prompt Engineer. This is a Full Time – Contract position with a duration of 13 Months. The role requires 3 days onsite and 2 days remote work. As an AI Prompt Engineer, you will be responsible for designing, refining, and optimizing context-aware LLM prompts for specialized cyber defense, threat intelligence, and vulnerability validation workflows. You will also build automated evaluation harnesses and benchmarking frameworks to rigorously test prompt accuracy, robustness, and drift over time. Additionally, you will create automated workflows to ingest, normalize, and analyze security telemetry across SAST, DAST, WAF logs, and perimeter scanning feeds. Developing structured validation techniques and guardrails to ensure AI-generated findings are precise, actionable, and verified is a key responsibility. You will partner with security researchers, penetration testers, and software engineers to automate manual triage and accelerate incident analysis at enterprise scale. Finally, you will continuously monitor LLM advancements to pilot novel AI capabilities for proactive attack surface management.

Requirements

Advanced prompt engineering (few-shot, chain-of-thought, structured outputs), LLM evaluation harnesses, automated benchmarking, and agentic workflows.
Vulnerability management (CVE/CWE triage), attack surface management (ASM), perimeter reconnaissance, and WAF testing/tuning.
Working familiarity with SAST/DAST tooling outputs and security telemetry correlation.
Practical experience querying and managing datasets using relational databases (specifically PostgreSQL) and scripting automated pipelines.
Demonstrated capability to minimize hallucinations and validate high-stakes security findings.
Must be able to be engaged on a W-2 basis.

Responsibilities

Design, refine, and optimize context-aware LLM prompts for specialized cyber defense, threat intelligence, and vulnerability validation workflows.
Build automated evaluation harnesses and benchmarking frameworks to rigorously test prompt accuracy, robustness, and drift over time.
Create automated workflows to ingest, normalize, and analyze security telemetry across SAST, DAST, WAF logs, and perimeter scanning feeds.
Develop structured validation techniques and guardrails to ensure AI-generated findings are precise, actionable, and verified.
Partner with security researchers, penetration testers, and software engineers to automate manual triage and accelerate incident analysis at enterprise scale.
Continuously monitor LLM advancements to pilot novel AI capabilities for proactive attack surface management.