Klue

Senior Software Engineer, Agents

Vancouver, British Columbia, CanadaFull timeSeniorC$140,000 - C$230,000 / yearPosted 12 days ago
Apply on Klue →

Sign into see who you know at Klue.

AT KLUE https://klue.com/, WE’RE BUILDING THE FUTURE OF COMPETITIVE INTELLIGENCE

👋 KLUE ENGINEERING IS HIRING!

We're looking for a Senior Software Engineer to join our team in Vancouver, someone excited to build and optimize state-of-the-art LLM-powered agents at scale. You'll bring a builder's mindset, scientific rigor, and relentless customer focus. You'll have an outsized impact on the product while staying close to the frontier of AI.

You will shape how we build and operate AI agents at scale, from multi-agent orchestration and sub-agent design to the eval frameworks that keep outputs trusted and measurable. This means optimizing across the full stack: inference costs at scale, retrieval and query performance, and the feedback loops that make agents genuinely improve over time.

You won't just execute on the roadmap, you'll help shape it, bringing a technical point of view on where the product should go and working closely with product leadership to get there. In this role, you will own projects end-to-end, guiding architecture decisions, experimentation strategy, and production readiness for our LLM-powered agents.

WHAT YOU'LL DO

- Build and ship backend systems that power agentic workflows. You design retrieval pipelines, orchestration layers, and multi-step agent architectures that turn millions of competitive data points (news, press releases, webpage changes, Slack posts, emails, reviews, CRM data) into actionable intelligence for our customers.

- Improve LLM-powered workflows end to end. From prompt design and retrieval strategy to caching and latency optimization, you'll make our agent responses faster, more accurate, and more reliable in production.

- Own evaluation of agentic systems at scale. You develop and operate evaluation frameworks (automated, offline, and human-in-the-loop) that measure relevance, quality, latency, and end-to-end task success across our agent pipelines. You'll define what "good" looks like and build the in...