TorontoFull TimeEngineering
Remotely
pythondockerkubernetesgcppytorchci/cdtransformersspacy
Job Description
📋 Description
- Build and ship backend systems powering agentic workflows for LLM-powered retrieval and generation.
- Design retrieval pipelines, orchestration layers, and multi-step agent architectures at scale.
- Define evaluation frameworks to measure relevance, latency, and end-to-end task success.
- Optimize retrieval and ranking across hybrid retrieval, re-ranking, and query understanding.
- Improve end-to-end LLM-powered workflows, including prompt design and latency optimizations.
- Collaborate with product, infrastructure, and data teams to align technical direction with product
🎯 Requirements
- Production experience building and operating backend systems, with a focus on search/retrieval
- Hands-on experience with search, retrieval, or ranking systems and information retrieval
- Experience with agentic/LLM-powered systems (retrieval-augmented generation, multi-step workflows).
- Strong software engineering fundamentals with Python, backend frameworks, APIs, and CI/CD.
- Familiarity with vector databases and search infrastructure (FAISS, PGVector, Pinecone, Weaviate
- Cloud infrastructure experience (AWS, GCP, or Azure) for scalable, low-latency systems.
🎁 Benefits
- Competitive compensation with equity options: CA$140K – CA$230K salary + equity.
- Office-First with hybrid flexibility; main hubs in Vancouver, Toronto, and London.
- Comprehensive benefits from Day 1 (health, dental, and perks).
- Ownership opportunities through Employee Stock Option Plan.
- Mac or PC provided and access to leading tooling.
- AI-first culture with opportunities to showcase work and influence product direction.
Back to all jobs