Research Scientist Graduate (High-Performance Computing (Inference Optimization) - Vision AI Platform)

4 Months ago • All levels • Research Development • $177,688 PA - $266,000 PA

Job Summary

Job Description

The Doubao (Seed) Vision AI Platform team seeks a Research Scientist Graduate (PhD) to start in 2025. Responsibilities include designing and developing next-generation large model inference engines, optimizing GPU cluster performance for image/video generation and multimodal models. This involves CUDA/Triton kernel development, TensorRT optimization, distributed inference strategies, quantization, and PyTorch compilation. The role also includes building GPU inference acceleration stacks and collaborating with algorithm teams on performance bottleneck analysis and software-hardware co-design. The ideal candidate possesses expertise in GPU programming, model quantization, parallel computing, or compiler optimization, and a deep understanding of Transformer architectures and LLMs.
Must have:
  • C++/Python proficiency
  • GPU programming expertise (CUDA/Triton/TensorRT)
  • Model quantization knowledge (PTQ/QAT)
  • Deep understanding of Transformer architectures and LLMs
Good to have:
  • Experience with large-scale inference systems
  • vLLM/TGI customization
  • Advanced quantization/sparsity techniques
Perks:
  • Medical, dental, and vision insurance
  • 401(k) savings plan with company match
  • Paid parental leave
  • Paid holidays and sick days
  • Paid Personal Time

Job Details

Responsibilities
About Doubao (Seed) Founded in 2023, the ByteDance Doubao (Seed) Team, is dedicated to pioneering advanced AI foundation models. Our goal is to lead in cutting-edge research and drive technological and societal advancements. With a strong commitment to AI, our research areas span deep learning, reinforcement learning, Language, Vision, Audio, AI Infra and AI Safety. Our team has labs and research positions across China, Singapore, and the US. Leveraging substantial data and computing resources and through continued investment in these domains, we have developed a proprietary general-purpose model with multimodal capabilities. In the Chinese market, Doubao models power over 50 ByteDance apps and business lines, including Doubao, Coze, and Dreamina, and is available to external enterprise clients via Volcano Engine. Today, the Doubao app stands as the most widely used AIGC application in China. Why Join Us Creation is the core of ByteDance's purpose. Our products are built to help imaginations thrive. This is doubly true of the teams that make our innovations possible. Together, we inspire creativity and enrich life - a mission we aim towards achieving every day. To us, every challenge, no matter how ambiguous, is an opportunity; to learn, to innovate, and to grow as one team. Status quo? Never. Courage? Always. At ByteDance, we create together and grow together. That's how we drive impact-for ourselves, our company, and the users we serve. Join us. Team Introduction The Doubao (Seed) Vision AI Platform team focuses on the end-to-end infrastructure development and efficiency improvement for Seed vision-based large model development, including the data pipeline construction and training, evaluation data delivery, and full lifecycle efficiency enhancement for visual large models such as VLM, VGFM, and T2I. This also encompasses large-scale training stability and optimization for acceleration, as well as large model inference and multi-machine multi-card deployment. We are looking for talented individuals to join our team in 2025. As a graduate, you will get unparalleled opportunities for you to kickstart your career, pursue bold ideas and explore limitless growth opportunities. Co-create a future driven by your inspiration with ByteDance. Successful candidates must be able to commit to an onboarding date by end of year 2025. We will prioritize candidates who are able to commit to the company start dates. Please state your availability and graduation date clearly in your resume. Applications will be reviewed on a rolling basis. We encourage you to apply early. Candidates can apply for a maximum of TWO positions and will be considered for jobs in the order you applied for. The application limit is applicable to ByteDance and its affiliates' jobs globally. Responsibilities: 1. Design and develop next-generation large model inference engines, optimizing GPU cluster performance for image/video generation and multimodal models to achieve industrial-grade low-latency & high-throughput deployment. 2. Lead inference optimization including CUDA/Triton kernel development, TensorRT/TRT-LLM graph optimization, distributed inference strategies, quantization techniques, and PyTorch-based compilation (torch.compile). 3. Build GPU inference acceleration stack with multi-GPU collaboration, PCIe optimization, and high-concurrency service architecture design. 4. Collaborate with algorithm teams on performance bottleneck analysis, software-hardware co-design for vision model deployment, and AI infrastructure ecosystem development.
Qualifications
Minimum Qualifications: 1. Bachelor's/Master's or above in Computer Science/EE/related fields. 2. Proficient in C++/Python and high-performance coding. 3. Expertise in ≥1 domains: GPU programming (CUDA/Triton/TensorRT), model quantization (PTQ/QAT), parallel computing (multi-GPU/multi-node inference), or compiler optimization (TVM/MLIR/XLA/torch.compile). 4. Deep understanding of Transformer architectures and LLM/VLM/Diffusion model optimization. Preferred Qualifications: 1. Experience in large-scale inference systems, vLLM/TGI customization, advanced quantization/sparsity; ByteDance is committed to creating an inclusive space where employees are valued for their skills, experiences, and unique perspectives. Our platform connects people from across the globe and so does our workplace. At ByteDance, our mission is to inspire creativity and enrich life. To achieve that goal, we are committed to celebrating our diverse voices and to creating an environment that reflects the many communities we reach. We are passionate about this and hope you are too. ByteDance Inc. is committed to providing reasonable accommodations in our recruitment processes for candidates with disabilities, pregnancy, sincerely held religious beliefs or other reasons protected by applicable laws. If you need assistance or a reasonable accommodation, please reach out to us at https://shorturl.at/cdpT2
Job Information
【For Pay Transparency】Compensation Description (Annually)

The base salary range for this position in the selected city is $177688 - $266000 annually.

Compensation may vary outside of this range depending on a number of factors, including a candidate’s qualifications, skills, competencies and experience, and location. Base pay is one part of the Total Package that is provided to compensate and recognize employees for their work, and this role may be eligible for additional discretionary bonuses/incentives, and restricted stock units.

Benefits may vary depending on the nature of employment and the country work location. Employees have day one access to medical, dental, and vision insurance, a 401(k) savings plan with company match, paid parental leave, short-term and long-term disability coverage, life insurance, wellbeing benefits, among others. Employees also receive 10 paid holidays per year, 10 paid sick days per year and 17 days of Paid Personal Time (prorated upon hire with increasing accruals by tenure).

The Company reserves the right to modify or change these benefits programs at any time, with or without notice.

For Los Angeles County (unincorporated) Candidates:

Qualified applicants with arrest or conviction records will be considered for employment in accordance with all federal, state, and local laws including the Los Angeles County Fair Chance Ordinance for Employers and the California Fair Chance Act. Our company believes that criminal history may have a direct, adverse and negative relationship on the following job duties, potentially resulting in the withdrawal of the conditional offer of employment:

1. Interacting and occasionally having unsupervised contact with internal/external clients and/or colleagues;

2. Appropriately handling and managing confidential information including proprietary and trade secret information and access to information technology systems; and

3. Exercising sound judgment.

Similar Jobs

Genies - Backend Engineer Intern (LLM)

Genies

San Mateo, California, United States (Hybrid)
4 Months ago
miniclip - Game Developer

miniclip

Türkiye (On-Site)
3 Weeks ago
Rebellion - Senior Gameplay Programmer

Rebellion

England, United Kingdom (Hybrid)
4 Months ago
Game freak - Game Programmer: Communication System [Leader]

Game freak

Chiyoda City, Tokyo, Japan (On-Site)
2 Months ago
playrix  - Lead C++ Software Engineer (Gameplay)

playrix

Georgia (Remote)
9 Months ago
Pulse Point - Sr. Machine Learning Engineer, AdTech

Pulse Point

United Kingdom (Remote)
4 Months ago
bytedance - Research Scientist Graduate (Foundation Model - Vision and Language)

bytedance

Seattle, Washington, United States (On-Site)
3 Months ago
Sony Interactive Entertainment - Lead AI/ML Engineer (Facial and Motion Generation)

Sony Interactive Entertainment

Tokyo, Japan (On-Site)
3 Months ago
bytedance - Research Scientist Intern (Doubao (Seed) - Foundation Model, Speech Understanding) - 2024 Summer (PhD)

bytedance

San Jose, California, United States (On-Site)
9 Months ago
Monzo - Senior Staff Machine Learning Scientist

Monzo

London, England, United Kingdom (Hybrid)
2 Months ago

Get notifed when new similar jobs are uploaded

Similar Skill Jobs

bytedance - Video Codec Algorithm Modeling Engineer - Multimedia Lab

bytedance

San Jose, California, United States (On-Site)
9 Months ago
bytedance - Student Researcher (Doubao (Seed) - Music Foundation Model) - 2025 Start (PhD)

bytedance

San Jose, California, United States (On-Site)
9 Months ago
Aeries technology - Sr. Software Engineer (C++)

Aeries technology

Bengaluru, Karnataka, India (On-Site)
2 Months ago
Marvell - Principal Engineer, System Design and Validation

Marvell

Ho Chi Minh City, Ho Chi Minh City, Vietnam (On-Site)
1 Year ago
zoox - Senior Software Engineer - Simulation Graphics and AI/ML

zoox

Seattle, Washington, United States (Hybrid)
6 Months ago
Techland - Junior Rendering Programmer

Techland

Wrocław, Lower Silesian Voivodeship, Poland (On-Site)
2 Months ago
Epic Games - Lead Automation Programmer

Epic Games

Montreal, Quebec, Canada (On-Site)
4 Months ago
Google - Software Engineer, Site Reliability Engineering

Google

Warsaw, Masovian Voivodeship, Poland (On-Site)
3 Months ago
Critical mass - Senior Product Engineer - 3D

Critical mass

Toronto, Ontario, Canada (On-Site)
4 Weeks ago
Black Bery - QNX Senior Systems Software Developer

Black Bery

Shanghai, China (On-Site)
4 Weeks ago

Get notifed when new similar jobs are uploaded

Jobs in Seattle, Washington, United States

Nintendo - Sr Manager, Engineering Infrastructure and IT

Nintendo

Redmond, Washington, United States (On-Site)
7 Months ago
MiQ - Chief of Staff

MiQ

Chicago, Illinois, United States (On-Site)
1 Week ago
AI Fund - Founding Product Designer

AI Fund

San Francisco, California, United States (On-Site)
3 Months ago
IGT - Real Estate Portfolio Program Manager

IGT

Providence, Rhode Island, United States (On-Site)
2 Months ago
Granicus - Business Development Representative

Granicus

United States (Remote)
3 Weeks ago
Hedra - Senior Research Engineer

Hedra

San Francisco, California, United States (On-Site)
4 Months ago
Stord - Area Manager II

Stord

Atlanta, Georgia, United States (On-Site)
2 Weeks ago
Riot Games - Principal Animation Artist - Unpublished R&D Product

Riot Games

Los Angeles, California, United States (On-Site)
4 Months ago
Palo Alto Networks - Consulting Director, DFIR, Reactive Services (Unit 42)

Palo Alto Networks

Atlanta, Georgia, United States (Remote)
2 Months ago
Ramp - Senior Software Engineer | Elixir

Ramp

New York, United States (Hybrid)
1 Week ago

Get notifed when new similar jobs are uploaded

Research Development Jobs

Canva - Senior Machine Learning Engineer, Content Management & Distribution, Teams & Education

Canva

Auckland, Auckland, New Zealand (Remote)
3 Weeks ago
Ansys - R&D Engineer II

Ansys

Atlanta, Georgia, United States (On-Site)
1 Month ago
Azerion - Marketing Intern – Creative Video & AI Enthusiast

Azerion

Schiphol-Rijk, North Holland, Netherlands (Hybrid)
3 Weeks ago
eBay - Applied Researcher (T24)

eBay

Bengaluru, Karnataka, India (Hybrid)
2 Months ago
Dream Sports - Lead Machine Learning Scientist

Dream Sports

Mumbai, Maharashtra, India (On-Site)
1 Year ago
Plain - Founding AI Engineer

Plain

United Kingdom (Remote)
2 Weeks ago
Tekion Corp - Senior Applied Scientist

Tekion Corp

Bengaluru, Karnataka, India (On-Site)
3 Months ago
Qualcomm - AI SDK Software Engineer

Qualcomm

Shanghai, China (On-Site)
2 Months ago
reality.co - Machine Learning Engineer - Monopoly World

reality.co

London, England, United Kingdom (On-Site)
2 Months ago
Match Group - Sr. Software Engineer, Machine Learning

Match Group

Palo Alto, California, United States (Hybrid)
2 Months ago

Get notifed when new similar jobs are uploaded

About The Company

Founded in 2012, ByteDance's mission is to inspire creativity and enrich life. With a suite of more than a dozen products, including TikTok as well as platforms specific to the China market, including Toutiao, Douyin, and Xigua, ByteDance has made it easier and more fun for people to connect with, consume, and create content.

San Jose, California, United States (On-Site)

Pasig, Metro Manila, Philippines (On-Site)

Taguig, Metro Manila, Philippines (On-Site)

San Jose, California, United States (On-Site)

View All Jobs

Get notified when new jobs are added by bytedance

Level Up Your Career in Game Development!

Transform Your Passion into Profession with Our Comprehensive Courses for Aspiring Game Developers.

Job Common Plug