🛠 Tech Stack

💼 About This Role

You'll design and build LLM-powered retrieval agents that automate complex workflows for competitive intelligence. You'll own the evolution of search and retrieval systems from prototype to production. Join a high-growth team redefining how users discover insights.

🎯 What You'll Do

• Design and implement RAG systems with agentic workflows
• Build and optimize retrieval pipelines using BM25, dense retrieval, and re-ranking
• Develop evaluation pipelines for retrieval and generation
• Experiment with query rewriting, expansion, and classification

📋 Requirements

• Software engineering experience
• Information retrieval systems and search relevance expertise
• Python with frameworks like PyTorch, TensorFlow, or JAX
• LLM and RAG pipeline experience

✨ Nice to Have

• Agentic system design for LLM workflows
• Conversational search background
• Open-source contributions in retrieval or NLP

🎁 Benefits & Perks

• 🏖️ Flexible hybrid work in Toronto/Vancouver/London offices
• 💰 Equity for all full-time employees
• 🏥 Extended health & dental from Day 1
• 📈 Career development with coaching and performance reviews
• 🎉 Perks like Goodlife and Perkopolis discounts

📨 Hiring Process

Estimated timeline: 2-3 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3Onsite / Final Round· 60 min