Senior AI Researcher (Agentic Systems)

OpenSpace

Ottawa

Remote

CAD 140,000 - 210,000

Full time

2 days ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Fully remote working environment
Equity for all full-time roles
Flexible time off
$500 home office budget
Paid parental leave
In-person company retreats/virtual
Employee referral program
Employer 401k matching

Job summary

OpenSpace is seeking a Sr. AI Research Engineer to build agentic systems that reason across 360° imagery, point clouds, BIM models, and drawings. You will combine perception primitives with frontier models to produce verifiable, actionable answers for project teams.

You will design and implement retrieval-grounding on a spatially and temporally indexed site record, and craft tool surfaces for reading drawings and querying BIM elements.

Qualifications

  • 5+ years building ML systems, including at least one production success.
  • Strong fluency with vision-language models, embeddings, and retrieval.
  • Experience designing evaluations where ground truth is costly or contested.

Responsibilities

  • Design and build agent systems that plan and execute multi-step tasks across imagery, geometry, and documents.
  • Own the context layer with retrieval grounding over a spatially indexed site record.
  • Define a tool surface for locating components and reading regions of drawings or BIM elements.
  • Build evaluations to determine readiness and ship readiness signals.
  • Choose models for steps, balancing frontier APIs, open weights, and production costs.
  • Ensure outputs are traceable to pixel, sheet, or spec sections.

Skills

ML systems
LLM/VLM proficiency
Python
multimodal retrieval
grounding reasoning
cost/tradeoff analysis

Education

MS/PhD in a related field

Tools

Python

Job description

  • The Sr. AI Research Engineer will build agentic systems that reason across the full OpenSpace data record: 360° imagery, point clouds, BIM models, drawing sets, and specifications, plus the newer streams coming off mobile capture, wearables, and field audio
  • Our computer vision team builds the perception primitives that determine what is in a capture. You will build the layer above, combining those primitives with frontier models to answer the questions project teams actually ask, and making the answers verifiable enough that a builder will act on them
  • The work is applied research. The hard problems are deciding what an agent should see out of a four-dimensional site record, designing the tools it can call, and proving it is right often enough to ship. By the time you are calling a frontier API, the interesting decisions have already been made
  • Design and build agent systems that plan and execute multi-step tasks across imagery, geometry, and documents
  • Own the context layer. Build retrieval and grounding over a spatially and temporally indexed site record so an agent gets the evidence a question actually needs
  • Design the tool surface: the primitives an agent calls to locate a component, compare two captures, read a region of a drawing, or query a BIM element
  • Build evaluations for tasks where ground truth is ambiguous, then use them to make honest calls about what is ready and what is not
  • Choose the right model for each step. Frontier API, open-weight model, fine-tuned small model, or classical CV, weighed against cost, latency, and accuracy at production volume
  • Make outputs traceable. Every claim should point back to the pixel, sheet, or spec section that supports it
  • Prototype quickly, kill what doesn’t work, and partner with platform engineers to ship what does
  • This role requires working in English with U.S.-based teams
Benefits
  • Employee medical, dental, and vision benefits 100% paid
  • Fully remote working environment
  • Equity for all full-time roles
  • Flexible time off
  • $500 home office budget
  • Paid parental leave
  • In-person company retreats/virtual gatherings
  • Employee referral program
  • Employer 401k matching
  • Judgment about what is worth automating, and the willingness to say when the answer is nothing yet M.S./Ph.D. in a related field or equivalent industry experience
  • Strong multimodal fluency: vision-language models, embeddings and retrieval, context design, and fine-tuning when it earns its cost
  • Experience designing evaluations from scratch where ground truth is expensive, sparse, or contested
  • Comfort with spatial data. You don’t need SLAM depth, but coordinate frames, camera poses, and projections shouldn’t slow you down
  • Solid engineering.
  • Python, async orchestration, tracing and cost instrumentation.
  • You build your own harness 5+ years building ML systems, including at least one LLM or VLM-based system you took to production and kept running
  • We will ask what broke Post-training or reinforcement learning on agent trajectories
  • Document understanding over technical drawings, specifications, or other structured PDFs
  • 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
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Senior Software Engineer (Backend, AI Platform)
Senior Software Engineer (Backend, AI Platform)

Affirm, Inc. • Ottawa

Remote
CAD 120,000 - 180,000
Remote-first compensation structure
Spending Wallets for tech, food, and生活
Health benefits
+2
Staff Engineer / AI Builder
Staff Engineer / AI Builder

F5 Remote Jobs • Canada

Remote
CAD 177,000 - 244,000
Staff AI Developer - Vancouver
Staff AI Developer - Vancouver

robotsandpencils • Vancouver

On-site
CAD 150,000 - 190,000
Staff AI Builder
Staff AI Builder

F5 Remote Jobs • Canada

Remote
CAD 177,000 - 244,000
Research Scientist- SLAM & VIO
Research Scientist- SLAM & VIO

mecka • Richmond Hill

On-site
CAD 100,000 - 160,000
Ground-truth data access
Challenging R&D projects
Machine Learning Software Engineer
Machine Learning Software Engineer

Ema • Vancouver

On-site
CAD 120,000 - 170,000
Principal Data Scientist, Agentic AI Technical Lead
Principal Data Scientist, Agentic AI Technical Lead

F5 Remote Jobs • Canada

Remote
CAD 180,000 - 260,000
Principal AI/ML Engineer
Principal AI/ML Engineer

Vanguard • Toronto

Hybrid
CAD 180,000 - 260,000
Principal Software Development Engineer - AI
Principal Software Development Engineer - AI

Quarry Consulting • Canada

Remote
CAD 120,000 - 180,000
AI Engineer
AI Engineer

Univedge Consulting LLC • Montreal

On-site
CAD 120,000 - 180,000