AI Software Engineer, Klue

• 5+ years of software engineering experience
• Experience with information retrieval systems, search relevance, and ranking models
• Expertise in Python, with experience in frameworks such as PyTorch, TensorFlow, or JAX
• Familiarity with LLMs, prompt engineering, and retrieval-augmented generation pipelines
• Understanding of evaluation methods for search systems, including offline metrics and user-facing evaluation
• Experience working with vector database infrastructure (FAISS, Milvus, Weaviate, Pinecone, PGVector) and traditional search engines (Elasticsearch, OpenSearch)
• Understanding of data pipelines, preprocessing, and large-scale data handling
• Ability to work independently and collaboratively in a fast-paced environment, balancing research and production needs
• Develop and implement CI/CD pipelines. Automate the deployment and monitoring of ML models
• Knowledge of query understanding, document summarization and other content enrichment strategies
• Expertise in automated LLM evaluation, including LLM-as-judge methodologies
• Skilled at prompt engineering - including zero-shot, few-shot, and chain-of-thought
• Experience with cloud infrastructure (AWS, GCP, Azure) for scalable ML workflows

Desirable

• We're looking for a Machine Learning Engineer to join our team in Toronto, focusing on building and optimizing state-of-the-art LLM-powered agents that can reason, plan and automate workflows for users
• You'll be joining us at an exciting time as we reinvent our insight generation systems, making this an excellent opportunity for someone with strong Backend and ML fundamentals who wants to dive deep into practical LLM applications
• As a member of our team, you'll be leading the design and implementation of search and retrieval agent systems that enable 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, ensuring that our systems remain scalable, efficient, and aligned with user intent
• Design 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 closely 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