Senior AI Engineer: LLMs, Agents & Security Platform

Ocupacao; United States; Remote; USD 150,000 - 210,000; Full time

Job summary

Checkmarx is seeking a Senior AI Engineer to join an R&D team building the AI-driven core of our product. You will design, implement, and own LLM-powered pipelines and agent-based systems that find, triage, and remediate security risk at scale in production.

The role emphasizes ground-truthing model behavior, evaluating tools and models, andscaling cloud-native architectures in Go. Strong knowledge of RAG, memory strategies, and observability is required.

Qualifications

• 5+ years of professional software engineering experience.
• Hands-on experience with LLMs and AI agents.
• Experience designing RAG pipelines, retrieval strategies, or context/memory systems for LLM apps.
• Experience evaluating model/agent quality (accuracy, latency, cost) and using evals to guide decisions.
• Experience with cloud AI services (AWS Bedrock, Azure OpenAI, Vertex AI).
• Strong proficiency in Go and/or Python.
• Solid understanding of distributed systems (message queues, gRPC/REST, relational DB) and Docker/Kubernetes.
• Strong testing, CI/CD, and observability fundamentals.
• Excellent English communication skills.

Responsibilities

• Design, build, and own LLM-powered pipelines and agent-based systems at scale.
• Design retrieval and context strategies grounding model behavior in product data.
• Define and run evaluations for model/agent quality and drive iteration.
• Evaluate emerging AI tools and provide build-vs-buy-vs-integrate recommendations.
• Stay ahead of AI landscape and translate developments into engineering proposals.
• Own reliability of AI features in production: guardrails, validation, observability.
• Participate in design discussions and code reviews with AI perspective.

Skills

LLMs & AI agents

Go

Python

Distributed systems

CI/CD & testing

English communication

Tools

Docker

Kubernetes

gRPC

REST APIs

Job description

Checkmarx is seeking a Senior AI Engineer to join an R&D team building the AI-driven core of our product. You will design, implement, and own LLM-powered pipelines and agent-based systems that find, triage, and remediate security risk at scale in production.

The role emphasizes ground-truthing model behavior, evaluating tools and models, andscaling cloud-native architectures in Go. Strong knowledge of RAG, memory strategies, and observability is required.