AI Engineer (LLM & Agentic AI)

This role is not for Edge

We're looking for an Applied AI Engineer to build and deploy production-ready AI systems at Aiden Risk. This role is ideal for an engineer who can turn LLM capabilities into reliable, scalable applications, from intelligent agents and retrieval systems to browser automation and data extraction.

What You'll Work On

• Build and optimize Retrieval-Augmented Generation (RAG) pipelines and vector search systems for real-world document datasets.
• Develop AI agents with tool calling, external API integrations, and automated workflows.
• Implement browser automation and web data extraction using Playwright.
• Integrate LLMs from OpenAI, Anthropic, Gemini, and open-source providers into production applications.
• Develop evaluation frameworks to measure AI accuracy, reliability, latency, and cost.
• Build, test, and deploy Python-based AI services using Docker and cloud platforms.
• Improve system performance, troubleshoot issues, and ensure reliability under real-world workloads.

What We're Looking For

• 1–2 years of software engineering experience with strong Python programming skills.
• Hands-on experience building applications using LLMs or generative AI models.
• Practical understanding of RAG, embeddings, vector search, and vector databases such as pgvector, Pinecone, or Chroma.
• Familiarity with AI frameworks such as LangChain or similar tools.
• Experience with browser automation tools such as Playwright is a plus.
• Basic understanding of APIs, Docker, and cloud platforms such as AWS or GCP.
• Strong problem-solving skills and an engineering mindset focused on building, testing, and deploying working solutions.

What Matters Most

We're looking for someone who has built practical AI applications beyond tutorials or demos and understands how to make them work reliably in production.