Sr Software Engineer, Video Intelligence

Vivint is seeking a Senior Video Intelligence Engineer to advance video understanding and improve camera intelligence and customer trust. The role develops video-language, summarization, context, and event-reasoning capabilities and partners with AI, platform, product, and app teams to bring models into production.

Responsibilities

Own VLM strategy, video-language understanding, temporal video reasoning, event understanding, and multimodal embeddings

Improve AI Video Search, video summarization, alert relevance, recognition support, and false-alert reduction

Build and evaluate systems that generate useful natural-language descriptions, insights, and summaries from video

Partner with AI, platform, product, and app teams to move models from research to production

Develop production evaluation methods for precision, recall, grounding, latency, safety, and customer usefulness

Guide architecture decisions across cloud, edge, and hybrid inference paths for video intelligence

Preferred

Experience generating natural-language descriptions, summaries, or searchable representations from video

Experience with multimodal foundation models, temporal video understanding, re-identification, or vector retrieval

Experience improving precision/recall, reducing false alerts, or evaluating customer-facing camera AI

Experience with smart home, security camera, IoT, edge/cloud, or real-time inference architectures

Experience with Docker, Kubernetes, GCP/AWS, or production model monitoring

Video Captioning

Video Summarization

Searchable Video Representations

Multimodal Foundation Models

Temporal Video Understanding

Re-Identification

Vector Retrieval

Precision

Recall Optimization

False Alert Reduction

Camera AI Evaluation

Smart Home Technology

Security Camera Systems

IoT

Edge

Cloud Architectures

Real-Time Inference

Docker

Kubernetes

GCP

AWS

Production Model Monitoring

Benefits

Other rewards may include annual bonus, short- and long-term incentives, and program-specific awards.

The position may be eligible to participate in the benefits program, which includes medical, vision, dental, 401K, and flexible spending accounts.

Hybrid schedule: in-office in Seattle, WA Monday through Thursday, with work from home on Friday; the position will start remote and then move into the hybrid schedule.

Company

Smart home security and automation systems with professional monitoring

Lehi, Utah, USA

http://www.vivint.com/

Founded in 1999

10001+ employees

Qualifications

Bachelor's degree in Computer Science, Software Engineering, AI/ML, or a related technical field, and 5+ years of professional experience in software development, applied science, or ML engineering; or

Master's degree in Computer Science, Software Engineering, AI/ML, or a related technical field, and 2+ years of professional experience in software development, applied science, or ML engineering

Experience with LLMs, vision-language models, multimodal AI, or generative AI systems

Strong Python software engineering skills

Experience processing, analyzing, or serving video content at scale

Familiarity with event detection, summarization, semantic understanding, embeddings, or model evaluation

Experience deploying AI services into production with Git and CI/CD workflows

Experience generating natural-language descriptions, summaries, or searchable representations from video

Experience with multimodal foundation models, temporal video understanding, re-identification, or vector retrieval

Experience improving precision/recall, reducing false alerts, or evaluating customer-facing camera AI

Experience with smart home, security camera, IoT, edge/cloud, or real-time inference architectures

Experience with Docker, Kubernetes, GCP/AWS, or production model monitoring

Bachelor’s degree in Computer Science, Software Engineering, AI/ML, or a related technical field, and 5+ years of professional experience in software development, applied science, or ML engineering; or

Master’s degree in Computer Science, Software Engineering, AI/ML, or a related technical field, and 2+ years of professional experience in software development, applied science, or ML engineering

Required skills

CI/CD, Event Detection, Git, Large Language Models (LLMs), Model Evaluation, Multimodal AI, Multimodal Embeddings, Production AI Deployment, Python, Video Processing, Video Summarization, Vision-Language Models

Experience

2+ years