Senior AI Engineer — LLM-Powered Retrieval & Agents

Klue; Toronto; On-site; CAD 120,000 - 170,000; Full time

Benefits offered by this job

Mac or PC provided

Employee Stock Option Plan

Extended health & dental coverage

Job summary

Klue is hiring a Senior Software Engineer in Toronto to build and optimize state-of-the-art LLM-powered agents that reason, plan and automate workflows for users. You will own end-to-end design of search and retrieval pipelines, evaluate agent systems, and push for production-ready, scalable solutions.

You'll collaborate with product, infra, and data teams, ship features with a customer-centric mindset, and help shape architecture decisions while staying ahead of advances in retrieval, LLMs and

Qualifications

• Experience building and operating backend systems in production across search/retrieval, data pipelines, distributed systems, or API-heavy architectures.
• Experience building or evaluating agentic/LLM-powered systems, including retrieval-augmented generation and multi-step workflows.
• Strong software engineering fundamentals: clean, well-tested code, Python, APIs, and production infra; focus on reliability and CI/CD.

Responsibilities

• Build and ship backend systems powering agentic workflows and retrieval pipelines.
• Own evaluation of agentic systems at scale with automated, offline, and human-in-the-loop tests.
• Design and optimize retrieval and ranking systems, balancing BM25, dense retrieval, and hybrids.
• Improve LLM-powered workflows end-to-end, including prompts, caching, and latency optimization.
• Collaborate with product, infra, and data teams to align technical direction with goals.

Skills

Backend systems in prod

Search/Retrieval/Ranking

Agentic/LLM-powered systems

Software engineering fundamentals

Vector databases

Cloud infra (AWS/GCP/Azure)

AI coding tools

Customer-focused delivery

Project leadership

Tools

FAISS

PGVector

Pinecone

Weaviate

Elasticsearch/OpenSearch

Job description

Klue is hiring a Senior Software Engineer in Toronto to build and optimize state-of-the-art LLM-powered agents that reason, plan and automate workflows for users. You will own end-to-end design of search and retrieval pipelines, evaluate agent systems, and push for production-ready, scalable solutions.

You'll collaborate with product, infra, and data teams, ship features with a customer-centric mindset, and help shape architecture decisions while staying ahead of advances in retrieval, LLMs and