SDE III - GPU Engineer at Glance

Bengaluru, Karnataka, India

Apply Now

Not SpecifiedCompensation

Senior (5 to 8 years)Experience Level

Full TimeJob Type

UnknownVisa

Technology, E-commerce, AIIndustries

Requirements

4+ years of experience in systems or ML engineering, with 2+ years working on GPU or accelerator optimization
Strong hands-on skills with CUDA programming, memory hierarchies, warps, threads, and shared memory
Familiarity with profiling tools (Nsight, nvprof, CUPTI) and performance analysis
Working knowledge of PyTorch, JAX, or TensorFlow internals
Proficiency in C++ and Python
Experience with mixed precision, FP16/BF16, or quantization
Deep curiosity about system bottlenecks and numerical correctness
Preferred Qualifications
Experience building fused operators or integrating custom kernels with PyTorch extensions
Understanding of NCCL / distributed inference frameworks
Contributions to open-source GPU or compiler projects (Triton, TVM, XLA, TensorRT)
Familiarity with multi-GPU / multi-node training and inference setups

Responsibilities

Develop, optimize, and maintain GPU kernels (CUDA, Triton, ROCm) for diffusion, attention, and convolution operators
Profile end-to-end inference pipelines (data movement, kernel scheduling, memory transfers) to identify and resolve bottlenecks
Apply techniques like operator fusion, tiling, caching, and mixed-precision compute to maximize GPU throughput
Collaborate with researchers to productionize experimental layers or model architectures
Build benchmarking tools and micro-tests for latency, memory, and throughput regressions
Integrate kernel improvements into serving stacks, ensuring reliability and repeatable performance
Work with platform teams to tune runtime configurations and job scheduling for GPU utilization

Skills

Key technologies and capabilities for this role

CUDATritonROCmStable DiffusionTransformersGPU KernelsDiffusion OperatorsAttention MechanismsConvolution OperatorsModel InferenceProfilingVertex AIGeminiImagen

Questions & Answers

Common questions about this position

What experience level is required for this SDE III GPU Engineer role?

The role requires 4+ years of experience in systems or ML engineering, with 2+ years specifically working on GPU or accelerator optimization.

What technical skills are essential for this position?

Candidates need strong hands-on skills with CUDA programming, memory hierarchies, warps, threads, and shared memory, along with familiarity with profiling tools like Nsight, nvprof, and CUPTI, and working knowledge of PyTorch, JAX, or TensorFlow internals. Proficiency in C++ and Python is also required.

What is the salary or compensation for this role?

This information is not specified in the job description.

Is this a remote position or does it require office work?

This information is not specified in the job description.

What kind of collaboration is involved in this role?

You'll work closely with research and infrastructure teams to productionize models and integrate improvements, and collaborate with researchers on experimental layers or architectures, as well as platform teams for tuning configurations.

Glance

Lock screen platform for personalized content

About Glance

Glance provides a unique digital experience by transforming the way users interact with their smartphones. Its main product, the Glance Lock Screen, allows users to access personalized content, products, and services directly from their lock screens, eliminating the need to search for apps. This is made possible through AI-powered personalization that curates content in an engaging format. Additionally, Glance has introduced Glance LIVE, which integrates live internet experiences into the lock screen. Another key offering is Roposo, a platform that combines live entertainment with shopping, allowing users to shop in real-time with creators. What sets Glance apart from competitors is its focus on delivering a seamless and visually appealing experience directly on the lock screen, as well as its commitment to supporting the creator economy through Roposo. The company's goal is to redefine internet consumption and empower creators while enhancing user engagement.

Bengaluru, IndiaHeadquarters

2019Year Founded

$379.4MTotal Funding

SERIES_DCompany Stage

Consumer Software, AI & Machine Learning, EntertainmentIndustries

1,001-5,000Employees

Benefits

Direct & Indirect Compensation

Employee Health Support

Caring for Families

Parental Leave

Core Hours

Generous Time Off Programs

Free and Discounted Products

4 hours/ Month Paid Volunteer Time

Risks

Privacy concerns may arise from AI-driven content personalization on lock screens.

U.S. market expansion faces competition from established players like Apple and Google.

Regulatory challenges in Indonesia could impact Roposo's live commerce integration.

Differentiation

Glance is the first 'screen zero' content delivery platform, redefining lock screen usage.

Roposo integrates live entertainment and commerce, pioneering creator-driven shopping experiences.

Glance's AI personalization delivers content directly to lock screens, enhancing user engagement.

Upsides

Glance's user base reached 300 million globally, showcasing rapid growth since 2019.

Roposo's expansion into Indonesia taps into a growing market for live video platforms.

Glance's partnerships with Verizon and Motorola facilitate U.S. market entry.

Land your dream remote job 3x faster with AI

Try Jobo Free