Research Engineer / Scientist - Storage for LLM

3 Days ago • All levels • $145,000 PA - $355,000 PA

Job Summary

Job Description

ByteDance's Infrastructure System Lab seeks a Research Engineer/Scientist to design and maintain a high-performance KV cache layer for LLM inference. Responsibilities include designing a distributed KV cache system for storing and retrieving intermediate states of transformer-based LLMs, optimizing low-latency access and eviction policies for long-context LLMs, collaborating with inference and serving teams, developing cache consistency protocols, implementing memory-aware sharding and replication strategies, monitoring system performance, and potentially extending open-source KV stores or building custom GPU-aware caching layers. This role requires expertise in large-scale distributed storage, caching infrastructure, and transformer-based model internals.
Must have:
  • PhD in relevant field
  • Strong understanding of transformer models and KV caching
  • Distributed systems & low-latency serving experience
  • High-performance compute environment familiarity (GPUs)
  • Proficiency in C++, Rust, Go, or CUDA
Good to have:
  • Experience building LLM inference-serving systems
  • Memory hierarchy optimization experience
  • GPU-to-GPU communication expertise
  • Cache-aware scheduling knowledge
Perks:
  • Competitive compensation
  • Generous research resources
  • Innovation-driven culture
  • Publication opportunities
  • Open-source contributions
  • Medical, dental, and vision insurance
  • 401k savings plan
  • Paid parental leave
  • Paid time off

Job Details

Responsibilities
About the Team The Infrastructure System Lab is a hybrid research and engineering group focused on building next-generation AI-native data infrastructure. Positioned at the intersection of databases, large-scale systems, and AI, the team leads innovation in areas such as vector and multi-modal databases, infrastructure optimization through machine learning, and LLM-based tooling like NL2SQL and NL2Chart. They also develop high-performance cache systems, including multi-engine key-value stores and LLM inference KV caches. The team thrives on collaboration, with researchers and engineers working closely to take ideas from paper to prototype to production. Their work supports key products used by millions and is regularly published and deployed at scale. About the Role We are seeking a systems researcher or engineer with deep expertise in large-scale distributed storage and caching infrastructure to design and maintain a high-performance KV cache layer for large language model (LLM) inference. This role focuses on improving latency, throughput, and cost-efficiency in transformer-based model serving by optimizing the reuse of attention key-value states and prompt embeddings. You’ll work on cutting-edge AI systems problems with real-world impact, alongside a world-class team. The role offers opportunities to publish, contribute to open-source, attend top conferences, and enjoy competitive compensation, generous research resources, and an innovation-driven culture. Responsibilities - Design and implement a distributed KV cache system to store and retrieve intermediate states (e.g., attention keys/values) for transformer-based LLMs across GPUs or nodes. - Optimize low-latency access and eviction policies for caching long-context LLM inputs, token streams, and reused embeddings. - Collaborate with inference and serving teams to integrate the cache with token streaming pipelines, batched decoding, and model parallelism. - Develop cache consistency and synchronization protocols for multi-tenant, multi-request environments. - Implement memory-aware sharding, eviction (e.g., windowed LRU, TTL), and replication strategies across GPUs or distributed memory backends. - Monitor system performance and iterate on caching algorithms to reduce compute costs and response time for inference workloads. - Evaluate and, where needed, extend open-source KV stores or build custom GPU-aware caching layers (e.g., CUDA, Triton, shared memory, RDMA).
Qualifications
Minimum Qualifications - PhD in Computer Science, Applied Mathematics, Electrical Engineering, or a related technical field. - Strong understanding of transformer-based model internals and how KV caching affects autoregressive decoding. - Experience with distributed systems, memory management, and low-latency serving (RPC, gRPC, CUDA-aware networking). - Familiarity with high-performance compute environments (NVIDIA GPUs, TensorRT, Triton Inference Server). - Proficiency in languages like C++, Rust, Go, or CUDA for systems-level development. Preferred Qualifications - Prior experience building inference-serving systems for LLMs (e.g., vLLM, SGLang, FasterTransformer, DeepSpeed, Hugging Face Text Generation Inference). - Experience with memory hierarchy optimization (HBM, NUMA, NVLink) and GPU-to-GPU communication (NCCL, GDR, GDS, InfiniBand). - Exposure to cache-aware scheduling, batching, and prefetching strategies in model serving.
Job Information
【For Pay Transparency】Compensation Description (Annually)

The base salary range for this position in the selected city is $145000 - $355000 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.

About Us

Founded in 2012, ByteDance's mission is to inspire creativity and enrich life. With a suite of more than a dozen products, including TikTok, Lemon8, CapCut and Pico 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.

Why Join ByteDance

Inspiring creativity is at the core of ByteDance's mission. Our innovative products are built to help people authentically express themselves, discover and connect – and our global, diverse teams make that possible. Together, we create value for our communities, inspire creativity and enrich life - a mission we work towards every day.

As ByteDancers, we strive to do great things with great people. We lead with curiosity, humility, and a desire to make impact in a rapidly growing tech company. By constantly iterating and fostering an "Always Day 1" mindset, we achieve meaningful breakthroughs for ourselves, our Company, and our users. When we create and grow together, the possibilities are limitless. Join us.

Diversity & Inclusion

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.

Reasonable Accommodation

ByteDance 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

Similar Jobs

Meta - Postdoctoral Researcher, Embodied AI (PhD)

Meta

Seattle, Washington, United States (On-Site)
5 Months ago
The Walt Disney Company - Manager, Software Engineer - Video Playback

The Walt Disney Company

Santa Monica, California, United States (On-Site)
2 Weeks ago
Google - Software Engineer II, AgentSpace

Google

Warsaw, Masovian Voivodeship, Poland (On-Site)
2 Days ago
NVIDIA - DevOps Engineering Intern, DGXC Console - Fall 2025

NVIDIA

Washington, United States (On-Site)
2 Weeks ago

Get notifed when new similar jobs are uploaded

Similar Skill Jobs

Google - Software Engineer III, Full Stack, Google Cloud Business Platforms

Google

Sunnyvale, California, United States (On-Site)
2 Weeks ago
Google - Senior Software Engineer, Recommendations, Ranking and Prediction, Google Workspace

Google

Sunnyvale, California, United States (On-Site)
2 Weeks ago
Enphase Energy - Sr. Software Engineer - Enlighten Cloud Backend

Enphase Energy

Bengaluru, Karnataka, India (On-Site)
3 Months ago
Zypp Electric - Social Media Manager

Zypp Electric

Gurugram, Haryana, India (On-Site)
10 Months ago
Enphase Energy - Staff Software Engineer

Enphase Energy

Bengaluru, Karnataka, India (On-Site)
4 Months ago
Workato - Senior Software Engineer (Rust)

Workato

(Remote)
7 Hours ago
Trend Micro - (Sr.) Data Engineer/AI Trainer

Trend Micro

Taipei City, Taiwan (On-Site)
7 Months ago
Passion Gaming - Back End Engineer PHP

Passion Gaming

Gurugram, Haryana, India (On-Site)
8 Months ago
ByteDance - Software Engineer, Inference

ByteDance

Seattle, Washington, United States (On-Site)
6 Months ago
IO Interactive - Multiplayer Programmer

IO Interactive

Brighton And Hove, England, United Kingdom (Hybrid)
1 Month ago

Get notifed when new similar jobs are uploaded

Jobs in San Jose, California, United States

Gloss Genius - Staff Software Engineer, Backend

Gloss Genius

New York, New York, United States (Hybrid)
8 Hours ago
Riot Games - Manager, Competitive Operations

Riot Games

Los Angeles, California, United States (On-Site)
1 Month ago
Rockstar Games - Tech Lead, Analytics Engineering

Rockstar Games

New York, New York, United States (On-Site)
1 Month ago
PlayStation Global - Principal Software Engineer, Graphics

PlayStation Global

Aliso Viejo, California, United States (On-Site)
1 Week ago
Jane Street - FTR Trader

Jane Street

New York, New York, United States (On-Site)
7 Hours ago
Netflix - Associate, FP&A, Finance & Operations

Netflix

Los Angeles, California, United States (On-Site)
2 Weeks ago
UPF Industries  - Assembler I

UPF Industries

Ooltewah, Tennessee, United States (On-Site)
1 Day ago
Universal Music - Vice President, Global Head of Fraud Prevention

Universal Music

California, United States (Remote)
1 Week ago
Daxko - Customer Service Advocate

Daxko

Birmingham, Alabama, United States (On-Site)
2 Weeks ago
Google - Customer Engineer II, Infrastructure Modernization, Biotech, Google Cloud

Google

Cambridge, Massachusetts, United States (On-Site)
2 Weeks ago

Get notifed when new similar jobs are uploaded

Similar Category Jobs

Looks like we're out of matches

Set up an alert and we'll send you similar jobs the moment they appear!

About The Company

Where imagination meets innovation, delivering limitless gaming experiences.

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

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

Dubai, Dubai, United Arab Emirates (On-Site)

New York, New York, United States (On-Site)

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

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

Seattle, Washington, 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
OSZAR »