Senior Software Engineer, AI (Agents)

Klue•Vancouver, BC

9d•Hybrid

About The Position

At Klue, we are building the future of competitive intelligence. Klue Engineering is seeking a Senior Software Engineer to join their team in Vancouver. This role focuses on building and optimizing state-of-the-art LLM-powered agents at scale, requiring a builder's mindset, scientific rigor, and customer focus. The successful candidate will have a significant impact on the product and stay at the forefront of AI advancements. The position involves shaping the development and operation of AI agents at scale, including multi-agent orchestration, sub-agent design, and evaluation frameworks to ensure trusted and measurable outputs. This includes optimizing the full stack, from inference costs and retrieval performance to feedback loops for agent improvement. The engineer will not only execute the roadmap but also contribute to its direction, providing technical insights and collaborating with product leadership. This role entails end-to-end project ownership, guiding architectural decisions, experimentation strategy, and ensuring production readiness for LLM-powered agents. Klue's mission is to help organizations win more deals by providing trustworthy, automated, and activated market, competitor, and buyer insights through AI agents. The company is AI-first, leveraging autonomous agents to collect intel, generate insights, and update content across departments, freeing up time from manual tasks. Klue's AI analyzes various data points to give product marketers and sellers a clear picture of market dynamics. The company fosters a culture of curiosity, ownership, and collaboration within a fast-growing, globally-distributed team.

Requirements

Experience building and operating backend systems in production, with meaningful experience in at least one of: search/retrieval, data pipelines, distributed systems, or API-heavy service architectures.
Experience building or evaluating agentic / LLM-powered systems, including retrieval-augmented generation, multi-step agent workflows, and critical evaluation of output quality at scale.
Strong software engineering fundamentals, including writing clean, maintainable, well-tested code, comfort with Python, and experience with backend frameworks, APIs, and production infrastructure, with a focus on reliability, observability, and CI/CD.
Familiarity with search and retrieval systems, having built or significantly improved retrieval pipelines and understanding information retrieval fundamentals (hybrid retrieval, relevance tuning, query understanding), and experience with tools like PGVector, Pinecone or Elasticsearch.
Experience with cloud infrastructure (AWS, GCP, or Azure) and building systems that handle scale, large data volumes, low-latency requirements, and high availability.
Proficiency in using AI coding tools like Copilot, Curssor, Claude Code, or similar to accelerate development workflow.
Customer-oriented mindset, demonstrated by shipping features based on understanding end-user problems and being motivated by customer impact.
Ability to lead projects and provide technical direction, owning problems end to end, making sound architectural decisions, and mentoring team members.

Nice To Haves

Experience designing multi-agent systems or complex orchestration workflows.
Contributions to AI/ML open-source projects.
ML fundamentals such as precision, recall, cross-validation, bias-variance tradeoff, overfitting and regularization.
Interest in sharing learnings externally (blog posts, talks, open-source contributions).

Responsibilities

Build and ship backend systems that power agentic workflows, designing retrieval pipelines, orchestration layers, and multi-step agent architectures to convert competitive data into actionable intelligence.
Improve LLM-powered workflows end to end, optimizing prompt design, retrieval strategy, caching, and latency to make agent responses faster, more accurate, and reliable in production.
Own evaluation of agentic systems at scale, developing and operating automated, offline, and human-in-the-loop evaluation frameworks to measure relevance, quality, latency, and end-to-end task success.
Design and build human-in-the-loop systems, proposing and prototyping feedback mechanisms, review workflows, and correction loops to maintain AI agent accuracy and trustworthiness, ensuring frictionless user experiences.
Ship with the customer in mind, connecting technical decisions to customer outcomes, understanding user behavior, prioritizing builds, shipping iteratively, measuring impact, and course-correcting quickly.
Collaborate across product, infrastructure, and data teams, aligning technical direction with product goals, contributing to architecture decisions, and establishing best practices for production-grade agentic systems.
Stay on the frontier, evaluating and integrating advances in LLMs, retrieval architectures, and agentic reasoning, bringing a forward-looking perspective to the work.

Benefits

High Performance Culture: Rewards high performance and growth through career development, coaching, and annual performance reviews.
Comprehensive benefits: Extended health & dental coverage that starts on Day 1.
Fun perks like discounts at Goodlife and Perkopolis.
Ownership: All full-time employees have the opportunity to participate in our Employee Stock Option Plan.
Vacation Policy is Take The Time You Need (with notice).
Top-tier tools: All employees receive a Mac (or PC) and access to A+ tooling.
AI First: All employees are encouraged to lean into AI to work smarter and faster, with opportunities to showcase AI-driven projects.
Growth / Leadership: Direct access to leadership team, including the CEO, and opportunities to connect with people across the company.
Social connection: Annual company-wide kickoff in Vancouver and regular social events in Hubs.
Dog-friendly spaces: Offices in Vancouver or Toronto are pup-approved.