B
RWA Job

Senior Recommendation System Engineer

Bybit
Kuala Lumpur, MalaysiaPosted 4mo ago

Role at a glance

Location
Kuala Lumpur, Malaysia
Level
Senior
Function
Engineering

Apply directly on Bybit’s site. RWA Signal does not collect applications.

About this role

RWA Signal Brief

This role involves building and maintaining high-concurrency recommendation engines that power Bybit's global digital asset exchange. The engineer will manage the full lifecycle of data pipelines, from real-time feature engineering with Kafka and Flink to optimizing vector retrieval systems like Milvus and Faiss. By focusing on low-latency inference and system stability, this position ensures that personalized trading and content experiences remain performant under extreme traffic.

  • 5+ years of recommendation system engineering at consumer-scale companies.
  • Proficiency in Go, Java, or C++ with strong CS fundamentals.
  • Hands-on experience with Spark, Flink, and Kafka stream computing.
  • Proven expertise in Milvus or Faiss cluster deployment and tuning.
  • Experience deploying PyTorch or TensorFlow models for online inference.
Recommendation EnginesGoDistributed SystemsVector DatabasesBig Data EngineeringModel Inference

Summary written by RWA Signal. The employer’s own description follows below.

About the role (from employer)

About Us

Established in 2018, Bybit is one of the world’s leading cryptocurrency exchanges and digital financial platforms, serving over 80 million users across more than 200 countries and regions. Powered by world-class technology and a user-first mindset, Bybit delivers a seamless ecosystem across trading, payments, wealth management, custody, institutional services, and Web3 — connecting users to the future of digital finance.
 
Our core values define how we build. We listen, care and improve to create products and experiences that put users first. Backed by a global team of ambitious builders, problem-solvers, and innovators, we foster a high-performance and fast-moving environment where talent is empowered to drive real impact at the global scale. Supported by 24/7 multilingual customer service and a strong commitment to innovation, we are shaping the future of finance through technology, collaboration, and bold execution.
 
Today, Bybit is recognized as one of the most trusted and transparent platforms in the digital asset industry, continuing to expand its global presence while building the infrastructure for the next generation of financial services.
Key Responsibilities
1. Recommendation Engine & Full-Pipeline Development
  • Multi-stage Engine Development: Own the development and refactoring of high-concurrency, low-latency recommendation serving engines, powering the full pipeline of multi-channel recall (two-tower/collaborative filtering/ANN vector retrieval) → coarse ranking → fine ranking → re-ranking.
  • Compute Tiering & Strategy Engine: Implement dynamic compute trimming and degradation mechanisms for dynamic Ul personalization and global strategy dispatch, ensuring core engine stability under extreme traffic spikes.
2. Real-time Feature Engineering & Data Consistency Governance
  • Real-time Feature Pipeline: Build high-throughput, low-latency real-time feature streams on Kafka/Flink, enabling minute-level/second-level user pehavioral feature updates and dynamic sliding-window aggregations.
  • Feature Store: Contribute to the development of unified online/offline feature storage with stream-batch convergence architecture; deeply govern industrial-grade pain points such as "online/offline feature inconsistency" and "feature time-travel leakage," systematically improving online/offline feature consistency.
3. Large-scale Retrieval & Vector Infrastructure Optimization
  • Vector Retrieval System: Own the construction and optimization of large-scale vector retrieval systems (Faiss/Milvus/NSW) supporting candidate pools from tens of thousands to milions, lead index structure parameter tuning, achieving P99 retrieval latency < 100ms.
  • Multi-source Heterogeneous Indexing: Build unified Embedding Pipelines and high-performance inverted index services covering trading products, news, KOL content, on-chain signals, and other heterogeneous data sources.
4. High-performance Model Inference & Compute Optimization
  • Deep Model Engineering: Own high-performance online deployment and operator optimization of complex deep ranking models (e.g., DIN/SIM sequential models, MMoE/PLE multi-objective deep models).
  • Inference Graph & Compute Governance: Solve compute explosion in multi-task/multi-objective online inference through inference optimization (quantization, graph optimization, batching strategies) - targeting fine-ranking P99 latency < 200ms.
5. System Performance, Global Observability & Experimentation Infrastructure
  • High Availability & SLO: Ensure global recommendation service P99 latency < 200ms and system availability > 99.9%; write comprehensive overload protection, thread isolation, and disaster recovery degradation code.
  • Global Distributed Tracing: In complex multi-region/multi-site/multi-language cross-border IDC environments, build and maintain end-to-end distributed tracing and monitoring systems (e.g.,Jaeger/Prometheus), establishing minute-level root cause attribution and fault localization mechanisms.
  • Experimentation Platform Engineering: Contribute to A/B experiment traffic-splitting platform upgrades, engineering CUPED variance reduction and sequential testing mechanisms to reduce sample size requirements and accelerate algorithm iteration pipelines.
 
Requirements
  • Industrial-grade Hands-on Experience: 5+ years of recommendation system engineering at consumer-scale internet companies; must have deeply participated in or led architecture refactoring or launches of realtime recommendation systems serving tens of millions of users at scale. Proven experience building recommendation systems from 0→1 (not just maintaining mature systems) is strongly preferred.
  • Mastery of Engineering Foundations: Exceptionally solid low-level CS fundamentals; proficient in at least one of Go/Java/C++ (Go preferred given current stack; C++ experience a plus for future engine optimization); familiar with PyTorch/TensorFlow model online inference and deployment optimization.
  • Deep Expertise in Big Data & Retrieval: Hands-on with Spark/Flink/Kafka stack, with real experience solving stream computing latency and data backlog issues; proficient in Milvus/Faiss cluster deployment and tuning.
  • Engineering Perspective on Algorithms: Deep understanding of computational complexity and online bottlenecks of core algorithms (collaborative filtering, two-tower recall, multi-objective optimization MMoE/PLE); ability to interface smoothly with algorithm teams for high-quality, efficient engineering translation.
  • Excellent System Design Capability: Proven experience in actual development and core module design of recommendation platforms, feature platforms, experimentation platforms, or high-performance RPC frameworks at top-tier companies.

Why Join Us
At Bybit, we are committed to fostering a supportive and enriching work environment. 
Our benefits include:
- Study Growth Fund: We support your professional development and continuous learning.
- Internal Events: Participate in regular team-building activities, workshops, and events designed to promote collaboration and innovation.
- Global Collaboration: Be part of a diverse, international team, working alongside colleagues from around the world.
- Career Advancement: Access opportunities for growth and advancement within a rapidly expanding global company.
- Internal Mobility: Grow with us- Your long-term development is important to us. We offer internal job opportunities to help build your career path.

Source & provenanceThis job is published by Bybit on their own careers site (2 July 2026) and aggregated by RWA Signal.View original posting

Bybit in the news

Company profile →
Bybit RWA Earn Adds JPE, Tokenized SBI Japan High-Dividend Equity Strategy Built on Plume
Stocks

Bybit RWA Earn Adds JPE, Tokenized SBI Japan High-Dividend Equity Strategy Built on Plume

Bybit has expanded its RWA Earn platform by adding JPE, a tokenized product linked to a Japanese high-dividend equity strategy managed by SBI Asset Management. Launched on November 9, JPE marks the platform's first equity offering, moving beyond its previous focus on fixed-income strategies. The tokenization was handled by DigiFTTech, with Plume Network providing the infrastructure for the JPE wrapper distributed via Bybit. JPE holds JX, a token issued by DigiFT that represents a beneficial interest in the open-ended SBI Japan High Dividend Equity Fund (Growth Type), which first went on-chain in July. While JX is available to accredited or institutional investors under Singapore law, JPE is accessible to eligible Bybit users who complete identity verification. The product is not principal-protected and carries various risks, including Japanese equity, liquidity, and currency. This launch is significant for the RWA market as it broadens the range of tokenized assets from bonds to listed equities, reflecting a growing trend to bring traditional financial instruments onto blockchain rails.

cryptonews.netPublished by source: Added: Nov 10, 20267.5
Tokenized Fund Collateral Could Be A Game Changer For Franklin Templeton Stock
U.S. Treasuries

Tokenized Fund Collateral Could Be A Game Changer For Franklin Templeton Stock

Franklin Templeton has expanded its digital asset strategy through a new partnership with the cryptocurrency exchange Bybit, allowing the use of tokenized fund collateral. This collaboration integrates Franklin Templeton’s Benji tokenized money market fund directly into an active trading venue, marking a shift from simple wallet listings to operational on-chain collateral management. While the firm currently manages approximately $3.2 billion in digital asset AUM, this initiative serves as a test for the scalability of digital rails in lowering distribution costs. The move is viewed as a strategic experiment to determine if tokenized assets can effectively serve as margin collateral within high-frequency trading environments. Despite the innovation, analysts suggest the immediate impact on Franklin Templeton’s earnings remains limited compared to broader pressures on fees and net flows. Success hinges on the firm's ability to maintain rigorous risk control and custody standards via ByCustody while scaling its tokenized product suite. Ultimately, the initiative highlights the ongoing institutional effort to bridge traditional financial products with decentralized trading infrastructure.

simplywall.stAdded: Oct 7, 20267.5
Next Shiba Inu Search Heats Up as Franklin Templeton Puts $686M On-Chain and Pepeto Goes Live
News

Next Shiba Inu Search Heats Up as Franklin Templeton Puts $686M On-Chain and Pepeto Goes Live

Franklin Templeton has expanded its institutional crypto integration by enabling $686 million in tokenized money market fund shares to be used as trading collateral on the Bybit exchange. This initiative, launched on September 28, allows investors to pledge tokenized fund shares via ByCustody while continuing to earn yield on their underlying assets. By integrating these shares into major exchanges like Bybit, Binance, and OKX, the $1.83 trillion asset manager is bridging traditional finance with digital asset liquidity. This development signifies a shift where institutional capital seeks to maintain core holdings while gaining exposure to crypto markets without liquidating positions. While the article contrasts this institutional progress with speculative retail tokens, the core event highlights the growing utility of tokenized U.S. Treasury-backed funds in decentralized finance. The ability to use regulated, yield-bearing assets as collateral on centralized exchanges marks a maturing phase for the RWA sector. This trend underscores how traditional financial giants are increasingly treating blockchain rails as standard infrastructure for capital efficiency.

techbullion.comAdded: Oct 1, 20267.5