Senior AI Research Engineer, Agentic Systems (Remote)

OpenSpace; United States; Remote; USD 184,000 - 265,000; Full time

Benefits offered by this job

Medical coverage

PTOD

401(k) match

Parental leave

Home office stipend

Referral program

Company retreats

Job summary

OpenSpace, a US-based leader in AI-powered Visual Intelligence for construction, is hiring a Sr. AI Research Engineer. You will build agentic systems that reason over 360° imagery, BIM models, and field data to support on-site decision making.

You will design evaluations, select models, and ensure outputs are traceable to the source. The role requires 5+ years of ML experience, strong multimodal fluency, and a hands-on engineering mindset.

Qualifications

• MS/PhD in related field or equivalent experience.
• 5+ years building ML systems with at least one production LLM or VLM.
• Experience designing evaluations where ground truth is expensive, sparse, or contested.
• Strong multimodal fluency: vision-language models, embeddings and retrieval, context design, and fine-tuning when it earns its cost.
• Solid engineering: Python, async orchestration, tracing and cost instrumentation.
• Comfort with spatial data: coordinate frames, camera poses, and projections.
• Judgment about what is worth automating, and the willingness to say when the answer is nothing yet.

Responsibilities

• 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.

Skills

ML systems in production

Multimodal vision-language

Python engineering

Spatial data familiarity

Automation judgment

Education

MS/PhD in related field or equivalent experience

Tools

Python

Async orchestration

Tracing

Cost instrumentation

Job description

OpenSpace, a US-based leader in AI-powered Visual Intelligence for construction, is hiring a Sr. AI Research Engineer. You will build agentic systems that reason over 360° imagery, BIM models, and field data to support on-site decision making.

You will design evaluations, select models, and ensure outputs are traceable to the source. The role requires 5+ years of ML experience, strong multimodal fluency, and a hands-on engineering mindset.