Sr. AI Researcher, Agentic Systems

What you'll do

• Design agents that plan and execute multi-step tasks across imagery, geometry, and documents; build retrieval, grounding, and agent tools over site records.
• Develop evaluations for ambiguous-ground-truth tasks, select models based on cost, latency, and accuracy, and make outputs traceable to supporting evidence.
• Prototype and partner with platform engineers to ship systems into production.

What they ask for

• M.S./Ph.D. in a related field or equivalent industry experience.
• 5+ years building ML systems, including at least one LLM- or VLM-based system taken to production and maintained.
• Experience designing evaluations from scratch when ground truth is expensive, sparse, or contested.
• Strong multimodal fluency and engineering skills, including Python, async orchestration, tracing, and cost instrumentation; comfort with spatial data.

Nice to have

• Post-training or reinforcement learning on agent trajectories; document understanding over technical drawings, specifications, or structured PDFs.
• Experience with sensor streams beyond core imagery or in construction, robotics, geospatial, or another physical-world domain.

Pay

$181,000 - $230,000 CAD (base salary)

Tools

Python, LLM, VLM, vision-language models, embeddings, retrieval, async orchestration, classical CV

AI focus

Applied research and production development of agentic systems that retrieve, ground, evaluate, and reason across multimodal construction-site records, with evidence-traceable outputs.