OverviewKlueis building the future of competitive intelligence. We are hiring anSoftware Engineer, AIto join our team in Toronto. Focus on building and optimizing state-of-the-art LLM-powered agents that can reason, plan, and automate workflows for users. You will lead the design and implementation of search and retrieval agent systems enabling users to discover high-quality, relevant information with minimal effort. You will work at the intersection of LLM-powered agent workflows, retrieval pipelines, and evaluation frameworks to ensure our systems are scalable, efficient, and aligned with user intent.What you’ll do and bring is described below.ResponsibilitiesDesign and implement retrieval-augmented generation (RAG) systems with agentic workflows to refine query understanding, document retrieval, and response synthesis.Build and optimize retrieval pipelines using BM25, dense retrieval, hybrid retrieval, and re-ranking approaches.Develop evaluation pipelines for retrieval and generation, including offline metrics (recall, MRR, nDCG) and human-in-the-loop evaluations.Experiment with query rewriting, expansion, and classification to improve retrieval relevance.Collaborate with Product to bring ML-powered search agents into production.Profile, debug, and optimize the latency, accuracy, and scalability of retrieval and generation components.Contribute to the design of data pipelines for training retrieval and ranking models, including dataset curation, augmentation, and labeling workflows.Stay up-to-date with advancements in LLMs, retrieval techniques, and agent architectures,



evaluating opportunities to integrate them into our systems.What You Bring (Qualifications)Software engineering experienceExperience with information retrieval systems, search relevance, and ranking modelsExpertise in Python, with experience in frameworks such as PyTorch, TensorFlow, or JAXFamiliarity with LLMs, prompt engineering, and retrieval-augmented generation pipelinesUnderstanding of evaluation methods for search systems, including offline metrics and user-facing evaluationExperience with vector database infrastructure (FAISS, Milvus, Weaviate, Pinecone, PGVector) and traditional search engines (Elasticsearch, OpenSearch)Understanding of data pipelines, preprocessing, and large-scale data handlingAbility to work independently and collaboratively in a fast-paced setting, balancing research and production needsDevelop and implement CI/CD pipelines. Automate the deployment and monitoring of ML modelsKnowledge of query understanding, document summarization and other content enrichment strategiesExpertise in automated LLM evaluation, including LLM-as-judge methodologiesSkilled at prompt engineering - including zero-shot, few-shot, and chain-of-thoughtExperience with cloud infrastructure (AWS, GCP, Azure) for scalable ML workflowsNice to HaveExperience with agentic system design for LLM workflowsBackground in conversational searchContributions to open-source projects in the retrieval, NLP,



or LLM ecosystemsWhat Success Looks LikeTake ownership and run with ambiguous problemsJump into new areas and rapidly learn what's needed to deliver solutionsBring scientific rigor while maintaining a pragmatic delivery focusSee unclear requirements as an opportunity to shape the solutionOur Tech StackLLM platforms: OpenAI, Anthropic, open-source modelsML frameworks: PyTorch, Transformers, spaCySearch/Vector DBs: Elasticsearch, Pinecone, PostgreSQLMLOps tools: Weights & Biases, MLflow, LangfuseInfrastructure: Docker, Kubernetes, GCPDevelopment: Python, Git, CI/CDWork Model and LocationsOffice-First with a hybrid approach. Our hubs include Vancouver (HQ), Toronto, and London. In-office collaboration occurs on defined days. We value flexibility and collaboration across global teams.Our Commitment to YouHigh-performance culture with career development, coaching, and annual performance reviewsComprehensive benefits: extended health & dental coverage starting Day 1Employee Stock Option Plan for full-time employeesVacation policy: take the time you need with notice to your teamTop-tier tools: hardware and tooling to support workAI-first culture: encourage leveraging AI to work smarter and fasterGrowth and leadership opportunities, direct access to leadershipSocial events and dog-friendly spaces in some officesAbout KlueKlue helps organizations stop losing winnable deals by generating market, competitor, and buyer insights in a unified, trustworthy, automated platform that is activated across departments. We are AI-first and focused on meaningful, craft-driven work.CompensationCompensation Range: CA$115K - CA$149K#J-18808-Ljbffr

📌 Software Engineer, Ai - C$115,000 - C$149,000 A Year (Winnipeg)
🏢 Klue
📍 Winnipeg