Skip to main content

Sr. AI Researcher, Agentic Systems

Summary by AIEngineer.careers

Sr. AI Researcher, Agentic Systems is a AI Research Engineer role (full-time). with OpenSpace. in VANCOUVER, CA. Compensation shown: $130K–$166K (est.). Imported listing (source: feeny.ai). Apply on the employer's site (feeny.ai).

Imported listing (source: feeny.ai) · Apply on feeny.ai

How our listings work

VANCOUVER · CA
$130K–$166K (est.)
Full-time
SENIOR
Apply Now

More AI jobs in Canada

The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.

Imported job description

Sourced from feeny.ai

OpenSpace is hiring a Sr. AI Research Engineer to build agentic systems over a rich spatial and visual data record, including 360° imagery, point clouds, BIM models, drawings, and specifications. The role combines perception primitives with frontier models to answer real project questions with verifiable, traceable outputs. This is applied research focused on context design, tool surfaces, and rigorous evaluation.

Responsibilities

  • Design and build agent systems that plan and execute multi-step tasks across imagery, geometry, and documents
  • Own the context layer with retrieval and grounding over a spatially and temporally indexed site record
  • Design the tool surface agents call to locate components, compare captures, read drawings, or query BIM elements
  • Build evaluations for tasks with ambiguous ground truth and make honest ship/no-ship calls
  • Select the right model per step across frontier APIs, open-weight models, fine-tuned models, and classical CV
  • Make outputs traceable back to pixels, sheets, or spec sections
  • Prototype quickly and partner with platform engineers to ship what works

Requirements

  • 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
  • Experience designing evaluations from scratch where ground truth is expensive, sparse, or contested
  • Strong multimodal fluency: vision-language models, embeddings and retrieval, context design, and fine-tuning
  • Solid engineering in Python, async orchestration, tracing, and cost instrumentation
  • Comfort with spatial data such as coordinate frames, camera poses, and projections

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, such as mobile capture, wearables, or field audio
  • Experience in construction, robotics, geospatial, or another domain where models meet the physical world

Tech Stack

Agentic SystemsAsync OrchestrationComputer VisionEmbeddingsFine-tuningLLMPythonReinforcement LearningRetrievalVision-Language ModelsVLM
OpenSpace

OpenSpace

San Francisco · US · 407+ employees

OpenSpace is a construction-technology software company founded in 2017 and headquartered in San Francisco. Its visual-intelligence platform captures construction-site reality using smartphones, 360-degree cameras, and drones, then turns that data into actionable project intelligence and workflows.

Weekly job alert

Get a weekly email when new AI engineering jobs match your filters. Free — confirm your address to start.

Related Jobs