Computer Vision Engineer

Computer Vision Engineer

Role Overview:

What You ll Do

• Design and implement advanced

  computer vision algorithms

  for:

• Image quality enhancement

• Blur/glare detection

• Super-resolution

• Color normalization

• Build

  deep learning models

  using

  PyTorch

  trained on

  large-scale visual datasets

  , from prototyping to deployment.
• Maintain robust

  vision pipelines

  with

  OpenCV

  ,

  Albumentations

  ,

  YOLO (Ultralytics)

  , and

  Segment Anything (SAM)

  .
• Deploy models via

  Docker/Kubernetes

  and integrate into

  cloud-native systems

  (AWS/GCP).
• Define, track, and optimize

  quantitative image quality metrics

  for automated evaluation and monitoring.
• Collaborate across

  product, design, QA, and data teams

  to translate user needs into engineering solutions.
• Contribute to

  exploratory R&D

  around

  LLMs

  ,

  vision-language models

  , and

  tool-using agents

  supported by a strong learning environment.
• Stay up to date with research in

  NeRFs

  ,

  diffusion models

  ,

  generative vision

  , and

  multimodal systems

  .

Minimum Qualifications

• 4+ years of

  professional software/ML development experience

  .
• 3+ years of hands-on experience building

  computer vision applications

  at scale.
• Strong command of

  Python

  , with deep familiarity using

  PyTorch

  and

  OpenCV

  .
• Experience developing and training

  deep learning architectures

  (CNNs, transformers) for visual tasks.
• Solid understanding of

  image processing

  ,

  data augmentation

  , and

  model evaluation metrics

  .
• Hands-on experience with

  Docker

  ,

  Git

  , and cloud services (

  AWS

  ,

  GCP

  , or similar).
• Interest in learning or contributing to

  LLM-based systems

  and

  multimodal AI pipelines

  .

Preferred Qualifications

• Experience with models/tools like:

• YOLOv5/v8

  ,

  Detectron2

  ,

  SAM

  ,

  OCR pipelines

• Familiarity with:

• CLIP

  ,

  BLIP

  ,

  vision-language models

• LangChain

  ,

  AutoGen

  ,

  CrewAI

  or similar tool-using frameworks
• Exposure to

  vector databases

  like

  FAISS

  ,

  Weaviate

  , or

  Pinecone

• Background in

  generative models

  (GANs, diffusion),

  video analytics

  , or

  multimodal learning

• Publications, personal projects, or open-source contributions in CV/AI are a plus