Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
Arrive AI IncPosted 3 days ago

Senior Computer Vision Engineer

Who we'd reach at Arrive AI IncFound and reached by Power Apply
Best leadEngineering lead

Leads the team you would join

CTO

Signs off on engineering hires

Technical recruiter

Owns the opening

Power Apply

From your own Gmail and LinkedIn.

About the role

This is an on-site senior computer vision role in Fishers, Indiana, for engineers who own the vision pipeline on Arrive AI's edge delivery hardware. The work runs from camera capture through model inference on NVIDIA Jetson devices to the events and cloud data the platform relies on. The product is the Arrive Point smart locker used for autonomous last-mile delivery, and the role sits within the company's product team.

What you’ll do

  • Own the vision stack from camera ingest through inference to the events and cloud data it produces.
  • Build and maintain C++ edge pipelines with DeepStream and GStreamer on Jetson Orin and Thor, using Triton and TensorRT.
  • Evaluate, train and fine-tune models, including CNNs, vision transformers, object detectors and vision-language models.
  • Export models through ONNX to TensorRT, build per-platform engines and check accuracy, latency and memory on the device.
  • Sample, curate and label data from deployed cameras, and address edge cases.
  • Run the training and release pipeline, including dataset versioning, evaluation gates, drift monitoring and retraining.
  • Work with the platform team on gRPC contracts with ArriveOS, the Rust-based edge orchestrator.
  • Containerize and deploy vision services to edge devices with Docker and K3s.
  • Design for privacy and security in video that may contain personal information.
  • Write architecture records and test reports, and present trade-offs to engineers and leadership.

What they’re looking for

  • A master's in computer science, computer vision, machine learning, electrical engineering or a related field with 3-5 years of industry experience, or a PhD with 3+ years.
  • A track record of shipping a vision system from camera to production.
  • Classical and modern computer vision experience, including PyTorch training and fine-tuning.
  • TensorRT and ONNX experience, including quantization and accuracy checks after conversion.
  • DeepStream and GStreamer for media pipelines.
  • Triton Inference Server, gRPC and API-driven development.
  • Experience with NVIDIA Jetson (Orin, Thor) or other edge compute such as Raspberry Pi.
  • Strong C++ (C++17 or later) and Python.
  • Experience collecting and labeling data on edge hardware, and adjusting camera and lighting conditions.
  • Docker, Kubernetes or K3s, CI/CD, and familiarity with AWS or Azure and S3-compatible storage.
  • Clear writing and presentation for technical and non-technical audiences.

Nice to have

  • Specific models such as YOLO, TinyViT, NVIDIA PeopleNet and the TAO Toolkit.
  • WebRTC, including SFUs, WHIP, TURN and STUN.
  • Unix domain sockets, shared memory, FlatBuffers or Protocol Buffers.
  • Camera hardware such as GigE, MIPI CSI-2, USB, V4L2, RealSense or time-of-flight sensors.
  • Rust or Go.
  • OCR and depth sensing.
  • MLOps practices such as dataset versioning, drift monitoring and label quality analysis.
  • RTSP, ONVIF and video management systems.
  • Background in logistics, delivery, retail or security video.
  • HIPAA familiarity and experience with on-prem only systems.

What’s on offer

  • Salary described as market competitive, with a high equity incentive.
  • Up to 5 days of travel per month.
  • No visa sponsorship is offered for this position.

Skills

Questions about this role

Is this role remote?

No. The posting says the role is on-site in Fishers, Indiana, and not remote.

Does the company sponsor visas?

No. The posting says visa sponsorship is not available for this position.

How much experience is required?

A master's with 3-5 years of industry experience, or a PhD with 3 or more years of industry experience.