Computer Vision Research Engineer

Applied Research Engineer - II (Computer Vision)

Who are we?

Generative AI

Read more about us:

Studio AI Product

Retail AI Product -

What are we looking for?

Senior Applied AI Researcher Computer Vision

Location:

What will you do?

• Lead Model Development:

  Architect and optimize deep learning models for image synthesis, enhancement, segmentation, and 3D scene understanding.

• Advance Generative AI:

  Fine-tune and innovate on diffusion and GAN architectures for photorealistic image generation, inpainting, and visual consistency.

• 3D Vision Innovation:

  Work on NeRFs, Gaussian Splatting, multi-view geometry, and depth estimation for realistic 3D reconstruction.

• Model Optimization & Deployment:

  Ensure scalable, low-latency deployment using Docker, Kubernetes, and ONNX in cloud production environments.

• Integrate AI Techniques:

  Blend diffusion models, transformers, and GANs for controllable image generation pipelines.

• Post-Processing & Ranking:

  Develop quality metrics and ranking algorithms to evaluate and improve visual outputs.

• Research Awareness:

  Stay on top of cutting-edge vision research and translate it into production-ready systems.

• Mentor & Collaborate:

  Guide junior engineers, collaborate with product and data teams, and drive end-to-end innovation.

What will make you successful in this role?

• Strong grasp of

  Generative AI

  — diffusion models, GANs, and hybrid architectures.
• Experience in

  3D Computer Vision

  — NeRFs, depth estimation, or multi-view geometry.
• Deep proficiency with

  PyTorch

  , OpenCV, and image transformation frameworks.
• Comfort deploying and scaling models across

  AWS/GCP/Azure

  using Docker/Kubernetes.
• Ability to optimize for

  real-time performance

  , profiling, and latency reduction.
• Research mindset with strong analytical and debugging instincts.
• Collaborative communication — can translate complex AI into product impact.

What you must have

• BTech / MTech / MS in Computer Science, AI, or related field (Tier-1/Tier-2 preferred)
• 3–5 years of hands-on experience in

  Computer Vision

  ,

  Generative AI

  , or

  3D Deep Learning

• Production experience with

  Diffusion/GANs

  ,

  3D reconstruction

  ,

  transformers

  , or

  scene understanding

• Strong command over

  Python

  ,

  PyTorch

  , and cloud-based deployment stacks

Why Spyne?

• Real-world AI at scale

  - build models that touch millions of car listings.

• Fast-track growth

  - high autonomy, direct impact, zero bureaucracy.

• Research + Product fusion

  - space to experiment, pressure to ship.

• A-Grade team

  - work with top-tier AI engineers and product minds.

• Tools & compute

  - everything you need for serious experimentation.

• Employee-first culture

  - full health coverage, transparent growth paths, and ownership opportunities.