Staff / Senior ML & CV Engineer - Grounding, Distillation

Enari Inc. (dba Verdun); United States; Hybrid; USD 150,000 - 230,000; Full time

Job summary

Enari Inc. (dba Verdun) is seeking a Staff/Senior ML & CV Engineer to strengthen grounding, distillation, and scalable perception capabilities. You will build detection, tracking, and VLM-driven reasoning systems that operate on real-world data.

You should ship robust models, balance quality with latency and cost, and contribute to training pipelines, evaluation tooling, and end-to-end model improvements in a production setting.

Qualifications

• Strong experience in computer vision, multimodal ML, or video understanding.
• Shipped models that had to work on real-world data, not just benchmarks.
• Comfortable across detection, tracking, representation learning, VLMs, and model optimization.
• Pragmatic about balancing quality, latency, and cost in production.

Responsibilities

• Detection and tracking models that ground higher-level reasoning.
• VLM selection, adaptation, and fine-tuning for security incident understanding.
• Temporal / multi-frame modeling so the system reasons over clips, not just frames.
• Image-quality handling: ROI-aware processing, low-light enhancement, denoise, super-resolution, and keyframe selection.
• Distillation of a lightweight first-pass model so the system stays accurate and cheap at scale.
• Tight loop with evals: hard negatives, false positives / negatives, and operator overrides into model improvements.

Skills

Computer vision

Multimodal ML

Video understanding

Python production

Tools

Python

Job description

Staff / Senior ML & CV Engineer - Grounding, Distillation

Build the detection, tracking, and VLM models that ground higher-level reasoning - and distill them so the system stays accurate and cheap at scale.

What you will own

• Detection and tracking models that ground higher-level reasoning
• VLM selection, adaptation, and fine-tuning for security incident understanding
• Temporal / multi-frame modeling so the system reasons over clips, not just frames
• Image-quality handling: ROI-aware processing, low-light enhancement, denoise, super-resolution, and keyframe selection
• Distillation of a lightweight first-pass model so the system stays accurate and cheap at scale
• Tight loop with evals: hard negatives, false positives / negatives, and operator overrides into model improvements

What we are looking for

• Strong experience in computer vision, multimodal ML, or video understanding
• Shipped models that had to work on messy real-world data, not just curated benchmarks
• Comfortable moving across detection, tracking, representation learning, VLMs, and model optimization
• Pragmatic about balancing quality, latency, and cost in production
• Production-quality Python and comfort with training pipelines, experimentation code, and model evaluation tooling

Especially valuable

• Activity recognition, VLM adaptation, or temporal video understanding
• Distillation, quantization, or small-model optimization
• Low-light imaging, robotics, autonomous systems, or safety-critical perception

Let’s build it together.