---
title: 'AI Vision Engineer at Nexxa.AI'
canonical: 'https://feeny.ai/job/ai-vision-engineer-nexxa-ai-san-francisco-abermqzmp3wj'
type: 'job'
last_seen: '2026-09-08'
---

# AI Vision Engineer at Nexxa.AI

- **Company:** Nexxa.AI
- **Location:** San Francisco, CA
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-08-27
- **Last confirmed live:** 2026-09-08
- **Apply:** https://jobs.ashbyhq.com/nexxa/7f3c4593-9157-4231-ac2d-ba004c8c430e

## Job description

Nexxa http://Nexxa.ai is building the best AI systems for heavy industries — enabling machines, systems and operations to think, decide and act autonomously across manufacturing, large-scale infrastructure, logistics and legacy environments. Our mission is to translate deep technical breakthroughs into operational reality, solving some of the hardest systems-level problems in industry.

## ROLE OVERVIEW

We are looking for an AI Vision Engineer to help design, build, and deploy next-generation computer vision systems across a diverse set of real-world industrial applications.

This role is ideal for someone with a strong foundation in Computer Vision and Machine Learning who is excited about working across the full vision stack, including classical and deep-learning-based CV, vision-language models (VLMs), multimodal reasoning, and real-time inference at the edge and in the cloud.

You will work closely with our AI and engineering teams to develop production-ready vision solutions, improve model performance, and help shape the next generation of intelligent visual systems.

## WHAT YOU'LL DO

- Design, train, evaluate, and deploy computer vision models for real-world industrial applications.
- Build and optimize CV pipelines for tasks such as object detection, segmentation, classification, OCR, tracking, and visual understanding.
- Develop and fine-tune vision-language models (VLMs) for multimodal reasoning, visual question answering, and document understanding.
- Design and optimize real-time inference pipelines for deployment on edge devices and in the cloud.
- Build scalable data pipelines for image and video collection, annotation, augmentation, training, and evaluation.
- Fine-tune and evaluate open-source vision and multimodal foundation models using modern training and inference frameworks.
- Develop robust evaluation frameworks and benchmarks to measure model accuracy, robustness, latency, and business impact.
- Optimize models for production constraints, including quantization, pruning, and hardware-accelerated inference.
- Collaborate with product, engineering, and research teams to translate business requirements into technical vision solutions.
- Contribute to architecture decisions, technical design reviews, and AI/CV best practices.
- Stay current with the latest advancements in computer vision, multimodal AI, and autonomous systems.

## REQUIRED QUALIFICATIONS

## EDUCATION

Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, Mathematics, Statistics, Artificial Intelligence, or a related technical field, or equivalent practical experience.

## EXPERIENCE & SKILLS

- 3+ years of industry experience in Computer Vision, Machine Learning, Applied AI, or related fields.
- Demonstrated experience independently owning and delivering computer vision projects from concept to production.
- Strong programming skills in Python.
- Hands-on experience with PyTorch and modern deep learning workflows.
- Experience developing and deploying computer vision models (detection, segmentation, classification, OCR) in production environments.
- Experience working with image and video processing libraries such as OpenCV.
- Experience with common CV/detection frameworks (e.g., YOLO, Detectron2, MMDetection, or similar).
- Experience working with VLMs, multimodal models, or Generative AI applications.
- Strong understanding of machine learning fundamentals, model evaluation, experimentation, and model deployment.
- Experience working with Hugging Face Transformers and open-source AI ecosystems.
- Familiarity with data annotation workflows, dataset curation, hyperparameter optimization, and inference optimization.
- Experience building production-grade software and AI systems.
- Strong analytical and problem-solving skills.
- Excellent communication and collaboration skills.

## PREFERRED QUALIFICATIONS

- Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Computer Vision, or a related field.
- Experience with OCR, document understanding, or visual reasoning systems.
- Experience with Vision-Language Models (VLMs) and multimodal AI applications.
- Familiarity with 3D vision, SLAM, or sensor fusion (e.g., camera + LiDAR) for industrial or robotics applications.
- Experience with real-time inference optimization (TensorRT, ONNX Runtime, quantization, pruning).
- Experience deploying models on edge hardware (e.g., NVIDIA Jetson, embedded systems).
- Experience with LangChain, LangGraph, or agentic AI frameworks combining vision and language models.
- Experience with vector databases and visual/semantic retrieval systems.
- Experience deploying AI systems on AWS, GCP, or other cloud platforms.
- Experience with Docker, Kubernetes, and MLOps workflows.
- Experience with PostgreSQL and large-scale data systems.
- Experience with model serving, distributed training, and inference optimization at scale.
- Contributions to open-source projects, technical blogs, research publications, Kaggle competitions, or other demonstrable CV/AI work.
- Experience working in startup or high-growth environments.

## WHAT WE'RE LOOKING FOR

- A builder who enjoys taking vision systems from prototype to production.
- Someone comfortable working across classical Computer Vision, deep learning, and multimodal Generative AI.
- An engineer who is curious, adaptable, and eager to learn emerging vision and AI technologies.
- A strong collaborator who can contribute across research, engineering, and product discussions.
- Someone excited about solving challenging real-world problems using computer vision.
- An individual who takes ownership, moves quickly, and thrives in an environment with significant autonomy.

Why Join http://nexxa.ai/Nexxa.AI http://Nexxa.AI?

- Innovative Environment: Play a critical role in transforming heavy industries through groundbreaking AI and automation technologies.
- Collaborative Culture: Be part of a team that values innovation, discipline, and continuous improvement.
- Professional Growth: Benefit from significant opportunities for career development and advancement.
- Competitive Compensation: Enjoy a comprehensive salary and equity package reflective of your expertise and contributions.

If you're passionate about development and eager to shape the infrastructure powering advanced AI solutions, we'd love to connect.

## About Nexxa.AI

## Company Overview
- **One-liner**: Nexxa.AI builds specialized multi-agent AI systems to automate industrial operations for heavy industries such as railroads, energy, construction, and manufacturing.
- **Entity Type**: Private (Seed-stage, Privately Held)
- **Headquarters**: Sunnyvale, California, United States
- **Founded**: 2024 (some sources list 2023)
- **Founders**: Philipp Wehn (CEO) and David Huang (CTO)

## Core Business
- **Primary industries**: Artificial Intelligence, Industrial Automation, Heavy Industries (Railroad, Energy, Construction, Mining, Manufacturing)
- **Target customers**: B2B, Enterprise – industrial engineering teams in project-heavy industries
- **Mission**: Build an AI system that works alongside industrial engineers to accelerate engineering productivity without pre-training, ultimately achieving industrial autonomy.

## Products & Services
- **Agentic AI Platform**: A multi-agent system that autonomously sets goals, defines success criteria, and executes operations directly into customers’ systems of record. Deployable on cloud or on-premise. Uses a combination of computer-use AI and computer vision.
- **Nitro (Intelligence/Own)**: Captures decision logic, institutional knowledge, and operational judgment from fragmented, legacy software stacks, enabling AI agents to act on unstructured data.
- **Full Self Computing**: A platform that processes unstructured data using generative AI for tasks like document analysis and decision-making.

## Market Standing
- **Valuation**: Not publicly disclosed
- **Total Funding**: USD 14.4 million
  - Pre-Seed (July 2025): $4.4M led by Andreessen Horowitz (a16z Speedrun)
  - Seed (January 2026): $9.0M led by Construct Capital
  - Non-Equity Assistance (November 2025): $1.0M from Amazon Web Services
- **Key Metric**: Annual Recurring Revenue (ARR) grew 4× in production within the automotive vertical
- **Growth Signals**: 400% headcount growth year-over-year (from ~2 to 26 employees); 8 active job postings; expanded presence to Canada
- **Notable Investors**: Andreessen Horowitz (a16z), Construct Capital, Amazon Web Services

## Competitive Advantages
- Deep specialization for heavy industries (railroad, energy, mining, manufacturing) rather than a horizontal AI platform
- AI agents are entirely owned by the customer – no shared models or data leakage
- Agents understand technical domain knowledge without any pre-training required
- Combines computer-use AI with computer vision to interact directly with legacy industrial systems

## Strategic Focus
- Expand across additional heavy industries (railroad, energy, construction, mining, manufacturing)
- Achieve “industrial autonomy” – AI that writes directly into systems of record, moving from recommendations to autonomous execution
- Scale from prototype to production in mission-critical environments, with deployment flexibility (cloud or on-premise)

## Why Work Here
- **High-growth startup**: 400% headcount growth YoY, backed by top-tier investors (a16z, Construct Capital, AWS)
- **Impactful mission**: Transform how industrial engineering teams work – days of repetitive work become minutes
- **Team culture**: Emphasis on “work together and grow together”, resilience, and open collaboration
- **Engineering-centric**: ~50% of team in technical roles (Applied AI Engineer, Senior AI Architect, etc.); active hiring across AI, product, and customer-facing roles
- **Locations**: Sunnyvale, CA (HQ) and Canada; remote/hybrid policy not explicitly stated but presence in two countries suggests flexibility
- **Perks**: Recent non-equity assistance from AWS, strong investor network, early-stage equity opportunity

## Sources
1. [nexxa.ai](https://nexxa.ai)
2. [LinkedIn - Nexxa.ai](https://www.linkedin.com/company/nexxa-ai)
3. [Crunchbase - Nexxa.ai](https://www.crunchbase.com/organization/nexxa-ai)
4. [Bloomberg - Nexxa AI Inc](https://www.bloomberg.com/profile/company/2584046D:US)
5. [PR Newswire - Funding Announcement](https://www.prnewswire.com) (implied from search results)

## Other roles at Nexxa.AI

- [Security & Infrastructure Engineer](https://feeny.ai/job/security-infrastructure-engineer-nexxa-ai-toronto-6kvymg7sm3c7) — Toronto, Canada
- [Security & Infrastructure Engineer](https://feeny.ai/job/security-infrastructure-engineer-nexxa-ai-san-francisco-5fvtj0rsjcyk) — San Francisco, CA
- [Staff DevOps Engineer](https://feeny.ai/job/staff-devops-engineer-nexxa-ai-toronto-sk6nc60ttm7t) — Toronto, Canada
- [Staff DevOps Engineer](https://feeny.ai/job/staff-devops-engineer-nexxa-ai-san-francisco-61tncfk1x35m) — San Francisco, CA
- [QA Engineer (AI Systems)](https://feeny.ai/job/qa-engineer-ai-systems-nexxa-ai-toronto-33wekf9anshf) — Toronto, Canada
- [QA Engineer (AI Systems)](https://feeny.ai/job/qa-engineer-ai-systems-nexxa-ai-san-francisco-1rwfk7sapb46) — San Francisco, CA
- [Backend AI Engineer](https://feeny.ai/job/backend-ai-engineer-nexxa-ai-toronto-ctswqxgx1cq1) — Toronto, Canada
- [AI Vision Engineer](https://feeny.ai/job/ai-vision-engineer-nexxa-ai-toronto-61gs4v0bx84p) — Toronto, Canada
- [Backend AI Engineer](https://feeny.ai/job/backend-ai-engineer-nexxa-ai-san-francisco-mk2v68wtjfcd) — San Francisco, CA
- [Applied AI Engineer](https://feeny.ai/job/applied-ai-engineer-nexxa-ai-munich-7g7m9w14c4f3) — Munich, Germany