Senior Software Engineer (ML Systems)

Voxel; United States; On-site; USD 150,000 - 190,000; Full time

Benefits offered by this job

Health, dental, and vision insurance

Equity Incentive Plan

Generous parental leave

Flexible work arrangements

In-office meals and team events

401K retirement plan

Job summary

Voxel is seeking an experienced ML/CV engineer to turn research-grade computer vision into scalable production systems. You’ll lead architecture decisions and drive features end-to-end, from prototype through rollout, with strong emphasis on observability and reliability.

You’ll own perception pipelines on a stream-processing stack (Flink/PyFlink), optimize model serving (Triton/TensorRT), and partner with teams across GTM and data ops to deliver measurable customer impact.

Qualifications

• 5+ years building and shipping production ML or computer vision systems.
• Experience with model serving and inference optimization (Triton, TensorRT).
• Proficiency in Python; knowledge of C++ or Go a plus.
• Experience with streaming/distributed data processing (Flink, Kafka).
• Familiarity with Kubernetes, Docker, and infrastructure as code (Terraform, ArgoCD); AWS experience.
• Technical leadership and cross-functional collaboration without formal authority.
• Experience with auto-labeling or embedding-based data search.
• Exposure to customer deployments or field-facing ML systems.

Responsibilities

• Turn research ideas into production features from prototype to rollout.
• Design and build perception pipeline components on stream-processing architecture (Flink/PyFlink).
• Own and improve production CV models, including training, evaluation, and inference optimization.
• Design logic converting model outputs into trustworthy incidents with state machines and probabilistic reasoning.
• Build observability into everything, including metrics and dashboards.
• Reduce end-to-end latency and cost while maintaining detection quality.
• Collaborate with GTM, customer success, and data ops for rollouts and labeling quality.
• Evaluate and integrate third-party ML tooling and drive adoption.
• Write design docs and de-risk changes with proofs of concept.

Skills

Python

C++ or Go

TensorRT

Flink

Kubernetes

Docker

Terraform

ArgoCD

AWS

Machine Learning / CV

Tools

TensorRT

Triton

Terraform

ArgoCD

Docker

Kubernetes

AWS

Flink

Job description

• Our perception team turns raw video into reliable, customer-facing incidents
• We’re re-architecting our perception system around stream-based processing, and we need an engineer who can take research-grade computer vision techniques and make them work in production: scalable, observable, and integrated cleanly into the wider product
• You’ll be a technical leader on the team, setting direction through design and execution rather than people management
• Turn research ideas (transformers, ensemble models, new detection and classification approaches) into production features, from prototype through evaluation, rollout, and iteration
• Design and build perception pipeline components on our stream-processing architecture (Flink/PyFlink), working with the platform team on model serving, configuration management, and orchestration
• Own and improve production CV models, including training, evaluation, and inference optimization (Triton, TensorRT, multi-backend serving)
• Design the logic that converts model outputs into trustworthy incidents: tracking, filtering, probabilistic reasoning, and state machines
• Build observability into everything you ship: metrics, dashboards, and evaluation loops that show whether a model or pipeline is working in the field
• Reduce end-to-end latency and cost while keeping detection quality high
• Partner with GTM, customer success, and data operations to plan customer rollouts, tune deployments, and improve labeling and review quality
• Evaluate and integrate third-party ML tooling (orchestration, labeling, dataset curation) and drive adoption across the team
• Write clear design docs and requirements, and de-risk major changes with proofs of concept before full buildouts
• You’ll have real influence over the architecture of a system that’s being rebuilt, with a direct line from your work to customer outcomes

Benefits

• Extensive / Generous health, dental, and vision insurance
• Highly competitive paid parental leave and support system
• Ownership in the business through an Equity Incentive Plan
• Generous paid time off and / or flexible work arrangements
• Daily meals in-office, vibrant company events, team-building
• 401K retirement plan, HSA options, pre-tax Commuter Card

Experience with model serving and inference optimization (Triton, TensorRT, or similar)Strong Python; working knowledge of C++ or Go is a plusSolid grounding in evaluation: building datasets, defining metrics, and detecting regressions before customers do5+ years building and shipping production ML or computer vision systems, with a track record of moving techniques from research to reliable productFamiliarity with Kubernetes, Docker, and infrastructure as code (Terraform, ArgoCD); AWS experienceExperience with streaming or distributed data processing (Flink, Kafka, or similar)Pragmatism: you know when a research result is ready for production and when it needs more workTechnical leadership without authority: you drive alignment across engineering, platform, GTM, and data ops through clear thinking and communicationExperience with auto-labeling or embedding-based data searchComfort with ambiguity: you help shape an architecture in flux and can validate it with a fast proof of conceptOwnership: you follow a feature past “the model works” to “customers trust it”Mentorship: you raise the bar for teammates through design reviews, code review, and sharing contextExposure to customer deployments or field-facing ML systemsExperience with the full CV data lifecycle: collection, sampling, labeling, and curation