Artificial Intelligence Engineer

detections-ai; California (MO); On-site; USD 150,000 - 190,000; Full time

Job summary

Detections.ai is seeking an AI LLM Engineer to drive development and optimization of large language models powering our detection engineering products. You will research, design, and implement LLM capabilities including retrieval-augmented generation and agentic workflows.

Work closely with ML engineers, product teams, and detection engineers to align AI capabilities with business goals and scale ML pipelines for real-time and batch use cases.

Qualifications

• Have 5+ years of experience in NLP, machine learning, or data science.
• Strong in Python and deep learning frameworks (PyTorch, TensorFlow).
• Hands-on experience building, testing, and deploying LLMs such as GPT-4, Gemini, or similar.
• Understand model training techniques, including data/model parallelism and distributed training.
• Are comfortable with cloud-native infrastructure (AWS or GCP) and distributed computing.
• Have experience with DevOps/MLOps/LLMOps practices.
• Thrive in a high-context, low-process environment.

Responsibilities

• Implement, fine-tune, and optimize state-of-the-art LLMs for performance, accuracy, and security use cases.
• Design and evaluate prompting strategies, flows, and application logic for LLM-powered features.
• Build and integrate advanced capabilities such as RAG, function calling, and code interpreter technologies.
• Design and deploy scalable ML pipelines for both batch and real-time use cases.
• Collaborate closely with ML engineers, product teams, and detection engineers to align AI capabilities with business goals.
• Lead the incubation of new AI initiatives and drive strategic technology choices in a microservices architecture.
• Stay current with the latest research in LLMs, agents, and large-scale training methods, applying insights directly into production systems.
• Document methodologies, models, and results to share across the team and company.

Skills

Python

PyTorch

TensorFlow

LLM deployment

NLP/ML

Cloud (AWS/GCP)

DevOps/MLOps

Distributed training

RAG frameworks

Agentic AI

Education

Master's or PhD in CS/AI or related

Tools

AWS

GCP

Docker

Terraform

GitHub Actions

OpenSearch

DynamoDB

Job description

Build the AI that makes detection engineers 10x more effective. Create cutting-edge LLM research to power ourdetection engineering community.

At Detections.ai, we're on a mission to 10x detection engineers. Security teams today are drowning in noisy tools and patchwork workflows. We're changing that—by building intuitive, AI-powered experiences that streamline how detection engineers write, test, and manage detections.

We combine deep expertise in cybersecurity, real-time systems, and applied AI to rethink how detection work gets done—from the ground up. Our team thrives on ownership, speed, and building for real users.

What You'll Do

We're looking for an AI LLM Engineer to drive the development and optimization of large language models that power our intelligent detection engineering products. You'll research, design, and implement cutting-edge LLM capabilities—from retrieval-augmented generation to agentic workflows—bringing AI into the critical path of security operations.

You’ll:

• Implement, fine-tune, and optimize state-of-the-art LLMs for performance, accuracy, and security use cases
• Design and evaluate prompting strategies, flows, and application logic for LLM-powered features
• Build and integrate advanced capabilities such as RAG, function calling, and code interpreter technologies
• Design and deploy scalable ML pipelines for both batch and real-time use cases
• Collaborate closely with ML engineers, product teams, and detection engineers to align AI capabilities with business goals
• Lead the incubation of new AI initiatives and drive strategic technology choices in a microservices architecture
• Stay current with the latest research in LLMs, agents, and large-scale training methods, applying insights directly into production systems
• Document methodologies, models, and results to share across the team and company

You’re a fit if you:

• Have 5+ years of experience in NLP, machine learning, or data science
• Are strong in Python (R is a plus) and deep learning frameworks (e.g., PyTorch, TensorFlow)
• Have hands-on experience building, testing, and deploying LLMs such as GPT-4, Gemini, or similar
• Understand model training techniques, including data/model parallelism and distributed training
• Are comfortable with cloud-native infrastructure (AWS or GCP) and distributed computing
• Have experience with DevOps/MLOps/LLMOps practices
• Thrive in a high-context, low-process environment

You’ll stand out if you:

• Hold a Master's or PhD in Computer Science, AI, or related fields
• Have experience building GenAI solutions using RAG frameworks or LLM agentic applications
• Bring direct experience applying AI in cybersecurity workflows
• Have strong research-to-production skills, bridging advanced ML concepts into deployable systems

Our Stack

• Frontend: React.js, Tailwind CSS, TypeScript
• Middle layer: Node.js, TypeScript
• Backend: Python (FastAPI)
• Infra & DevOps: AWS, GCP, Docker, Terraform, GitHub Actions
• Data: OpenSearch, DynamoDB
• AI Agents: Gemini, Anthropic, OpenAI
• Tooling: Figma, Storybook, CI/CD pipelines

Why Join Us?

• Build for real users: Work hand-in-hand with detection engineers
• Own meaningful problems: Ship features that matter
• Move fast, without red tape: Small, high-context team
• Make an outsized impact: You'll help shape both product and culture