Senior AI Engineer: LLM-Powered Agent Systems

Apply; Toronto; On-site; CAD 110,000 - 160,000; Full time

Job summary

Klue is seeking a Senior Software Engineer in Toronto to lead the design and development of LLM-powered retrieval and agentic workflows. You will build backend systems, optimize ranking pipelines, and own end-to-end production readiness for scalable intelligence tools.

You will work on retrieval-augmented generation, dense retrieval, and hybrid strategies, shaping architecture decisions and ensuring fast, accurate insights for customers.

Qualifications

• Experience building and operating backend systems in production.
• Hands-on experience with search, retrieval, or ranking systems.
• Experience building or evaluating agentic / LLM-powered systems.
• Strong software engineering fundamentals: Python, APIs, and production infrastructure; focus on reliability, observability, and CI/CD.
• Familiarity with vector databases and search infrastructure (FAISS, Elasticsearch, Pinecone, Weaviate, PostgreSQL).
• Experience with cloud infrastructure (AWS, GCP, or Azure).
• Use of AI coding tools (Copilot, Cursor, Claude Code) to accelerate development.
• Customer-oriented mindset with a track record of shipping user-focused features.
• Ability to lead projects and provide technical direction.

Responsibilities

• Build and ship backend systems that power agentic workflows.
• Own evaluation of agentic systems at scale.
• Design and optimize retrieval and ranking systems.
• Improve LLM-powered workflows end to end.
• Ship with the customer in mind and measure impact.
• Collaborate across product, infra, and data teams.
• Stay on the frontier by evaluating advances in LLMs and retrieval architectures.

Skills

Backend systems

Search/retrieval

Agentic/LLM-powered

Python

APIs

Reliability/Observability/CI/CD

Cloud infrastructure

Vector databases

Tools

FAISS

Elasticsearch

Weaviate

Pinecone

PostgreSQL

Docker

Kubernetes

GCP

Job description

Klue is seeking a Senior Software Engineer in Toronto to lead the design and development of LLM-powered retrieval and agentic workflows. You will build backend systems, optimize ranking pipelines, and own end-to-end production readiness for scalable intelligence tools.

You will work on retrieval-augmented generation, dense retrieval, and hybrid strategies, shaping architecture decisions and ensuring fast, accurate insights for customers.