{"id":5749,"date":"2025-05-29T06:26:29","date_gmt":"2025-05-29T06:26:29","guid":{"rendered":"https:\/\/www.odbms.org\/blog\/?p=5749"},"modified":"2025-05-29T06:27:13","modified_gmt":"2025-05-29T06:27:13","slug":"on-trading-tech-and-quant-development-interview-with-jad-sarmo","status":"publish","type":"post","link":"https:\/\/www.odbms.org\/blog\/2025\/05\/on-trading-tech-and-quant-development-interview-with-jad-sarmo\/","title":{"rendered":"On Trading Tech and Quant Development. Interview with Jad Sarmo"},"content":{"rendered":"\n
\n

Forecasting financial time series is one of the most complex tasks in data science.<\/em><\/p>\n<\/blockquote>\n\n\n\n

Q1. You\u2019ve been working in the Trading Tech and Quant Development space for the last 20+ years. What are the main lessons you\u2019ve learned through this experience? <\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: Back in 2004, I deployed the first automated trading system (ATS) for foreign exchange at a top-tier bank. We had to build software directly on traders\u2019 workstations to send algorithmic orders\u2014latency was measured in hundreds of milliseconds. <\/p>\n\n\n\n

Since then, the landscape has evolved dramatically: the proliferation of low-latency submarine fiber-optic cables, high-frequency signals bouncing off the ionosphere, the emergence of cloud computing, AI-assisted development, the rise of blockchain, and nanosecond-level FPGAs. <\/p>\n\n\n\n

Despite this, the core principles remain unchanged: a solid grasp of systems and markets, clear business objectives, and the ability to assemble the right experts to solve the right problems. Equally important\u2014especially as firms face increasing external scrutiny and apply for new licences\u2014is a commitment to compliance with applicable laws and regulations from the outset.<\/p>\n\n\n\n

A personal lesson I\u2019ve come to value is this: if you\u2019re comfortable, it\u2019s time to take a risk, learn, and repeat. That cycle is essential in such a fast-evolving landscape.<\/p>\n\n\n\n

Q2. What is your role at B2C2?<\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: B2C2 <\/a>are a global leader in the institutional trading of digital assets, serving institutions such as retail brokers, exchanges, banks, and fund managers. We provide clients and the market with deep, reliable pricing across all market conditions. <\/p>\n\n\n\n

I joined B2C2 in 2021\u2014during a pivotal year for digital assets\u2014to build our global Quantitative Development desk. My team works closely with traders, researchers, and engineers to improve client pricing, trading strategies, and automated risk systems.<\/p>\n\n\n\n

I also lead our Exchange Squad, which manages trading from market data ingestion to algorithm optimization across more than 30 AWS regions<\/a> globally.<\/p>\n\n\n\n

Q3. What are the main challenges in this industry when it comes to data management? Specifically, since you are handling liquid assets, what is the main challenge you’ve seen when an asset can be \u201ceasily\u201d converted into cash in a short amount of time? <\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: Like in any asset class\u2014FX, equities, rates\u2014crypto trading involves massive volumes of market and trading data. But crypto <\/a>adds a unique layer of complexity.<\/p>\n\n\n\n

It\u2019s a 24\/7 market, with both on-chain (blockchain<\/a>-logged) and off-chain (centralized exchanges) activity. A significant share of volume also flows through DeFi protocols<\/a> using smart contracts.<\/p>\n\n\n\n

We face challenges like inconsistent exchange APIs (REST, WebSocket, etc.), cloud-native environments, and the need for extremely low-latency systems that handle massive data bursts. Meanwhile, newer or illiquid tokens present formatting hurdles, with decimals occasionally extending to 10+ digits \u2014 far beyond what many traditional systems were designed to handle.<\/p>\n\n\n\n

Real-time hydration and normalization of incoming data streams are therefore critical to support both research and trading effectively.<\/p>\n\n\n\n

Q4. You mentioned in a previous presentation that managing a \u201cCrypto ecosystem\u201d is not an easy task. What is a Crypto ecosystem, and what is it useful for? What are the specific challenges you face, and how do you solve them?<\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: By \u201ccrypto ecosystem,\u201d I mean the global, interconnected infrastructure where digital assets are traded: exchanges, OTC counterparties, and all supporting systems.<\/p>\n\n\n\n

Each participant may be located in a different \u2014Virginia, Tokyo, London, and beyond. Our system ingests high-frequency data from across the world, unifies it, and processes it with both low latency and high throughput.<\/p>\n\n\n\n

The hardest part is normalizing inconsistent feeds so they\u2019re useful across trading and research. Historically, AWS prioritized reliability over low latency, but in recent years, the biggest players\u2014including B2C2\u2014have worked closely with AWS to re-architect the cloud to meet the latency needs of crypto trading.<\/p>\n\n\n\n

Q5. Let\u2019s talk about the use of AI and Machine Learning in the financial services industry. You cannot predict the market by training an AI model on historical data, because things change rapidly in the financial markets. How do you handle this issue? Does it make sense to use AI?<\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: Forecasting financial time series is one of the most complex tasks in data science.<\/p>\n\n\n\n

A picture of a dog from 10 years ago is still useful to train an image classifier\u2014but financial data ages fast. Market structure, participants, and behaviour shift constantly, so models need regular recalibration.<\/p>\n\n\n\n

Ensemble learning is particularly powerful in finance; rather than relying on a single predictive model, we combine many models that each perform slightly better than average. AI is not a crystal ball, but it provides meaningful signals that enhance traditional pricing and risk systems.<\/p>\n\n\n\n

Q6. You have been leveraging a vector-native data platform at B2C2. Could you please explain what you do with such a data platform?<\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: We use KX\u2019s kdb+ platform <\/a>to support our real-time and historical time-series data needs. It enables global ingestion across AWS regions, persistent storage, replay of massive tick datasets, and complex event processing.<\/p>\n\n\n\n

The consistency of this platform means researchers can focus on analysis without worrying about where the data lives. PyKX,<\/a> a Python\u2013Q<\/a> hybrid notebook interface, allows heavy computations to run in Q, while using Python for exploratory analysis and ML.<\/p>\n\n\n\n

KX also provides high-performance dashboards for quick data visualization\u2014even by non-technical users.<\/p>\n\n\n\n

Q7. Why not use a classical relational database or a key-value data store instead?<\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: Traditional relational databases are too rigid and slow for high-frequency time-series analytics. Key-value stores are great for quick lookups but lack native analytics support.<\/p>\n\n\n\n

Vector-native platforms like kdb+ are designed for exactly this use case. They let us run complex queries over billions of rows in milliseconds\u2014without reshaping the data or creating indexes.<\/p>\n\n\n\n

As data volume grows to terabytes per day, traditional databases become engineering bottlenecks. In contrast, vector platforms scale naturally, with each column and date efficiently mapped to files.<\/p>\n\n\n\n

Q8. Let\u2019s go a bit deeper. If you start with “FeedHandlers,\u201d how do you end up processing this complex data at scale, in real time and without losing some data?<\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: Our architecture begins with Java or Rust feed handlers that convert raw exchange data into kdb+ format.<\/p>\n\n\n\n

A ticker plant then routes data to three layers:<\/p>\n\n\n\n

            1          A real-time in-memory database<\/p>\n\n\n\n

            2          A persistent on-disk database<\/p>\n\n\n\n

            3          A complex event processor<\/p>\n\n\n\n

This setup ensures we can act on data instantly, store it reliably, and support deep analytics\u2014all with complete transparency for end users, whether they\u2019re consuming live or historical data.<\/p>\n\n\n\n

Q9. What about data quality? How do you ensure data quality in the various phases of data processing?<\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: Data quality starts with ingestion. Exchange feeds vary in reliability and format, so we normalize and hydrate the data immediately to remove inconsistencies.<\/p>\n\n\n\n

We maintain constant feedback loops between research and production teams to monitor and improve quality. Clean, consistent data is the backbone of everything\u2014without it, even the most sophisticated models won\u2019t perform.<\/p>\n\n\n\n

Q10. You decided to integrate AWS FSx for Lustre with kdb+. What are the main benefits of this design choice?<\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: AWS FSx for Lustre<\/a> has been a major improvement. It offers virtually unlimited horizontal scaling and high-speed access. We can connect dozens or hundreds of nodes, each with fast local disk and compute, to form a massive high-performance network file system.<\/p>\n\n\n\n

It compresses files efficiently, offloading that work from kdb+. We can spin up isolated research environments on demand without affecting production, and there\u2019s no downtime. Auto-scaling lets us right-size our infrastructure at any time.<\/p>\n\n\n\n

Compare that to traditional datacentres\u2014provisioning takes weeks and usually leads to overbuying hardware. In the cloud, it\u2019s a five-minute job.<\/p>\n\n\n\n

Q11. How is industry regulation affecting this complex data management?<\/strong><\/p>\n\n\n\n

Jad Sarmo<\/strong>: Regulation is advancing quickly. <\/ins>This means we must store data in auditable, retrievable formats. End-to-end traceability\u2014from ingestion to storage to downstream consumption\u2014is non-negotiable.<\/p>\n\n\n\n

This adds operational overhead, but it also emphasizes the need for trustworthy systems that meet both performance and compliance standards. We see this reflected in regulatory initiatives like the EU\u2019s MiCA regulation<\/a>, the approval of Bitcoin ETFs in the U.S.<\/a>, and the UK\u2019s FCA Discussion Paper DP25\/1<\/a>, which explores regulating crypto asset activities.<\/p>\n\n\n\n

……………………………………………………………<\/p>\n\n\n\n

\"\"<\/a><\/figure>\n\n\n\n

Jad Sarmo<\/strong>, Head of Quantitative Development | Expert in High-Performance Trading Systems, B2C2.<\/p>\n\n\n\n

Jad Sarmo is a technology and trading infrastructure leader with over 20 years of experience building high-performance trading systems for FX and digital asset markets. He<\/em> is <\/em>currently Head of Quantitative Development at B2C2, <\/em>a global leader in institutional liquidity for digital assets<\/em>, where he<\/em>oversees <\/em>a global team delivering real-time pricing, exchange trading, and analytics infrastructure across 24\/7 markets.<\/em><\/p>\n\n\n\n

Prior to B2C2, Jad ran Technology at Dsquare Trading, a high-frequency proprietary <\/em>FX <\/em>trading firm that <\/em>rose to prominence through cutting edge<\/em> algorithms, low-latency engineering, and a world-class team. There, he designed ultra-fast trading systems and led cross-functional teams through years of continuous innovation in a high-stakes environment.<\/em><\/p>\n\n\n\n

Jad speciali<\/em>se<\/em>s in bridging the gap between trading, quant research, and engineering \u2014 turning complex ideas into reliable, automated, and profitable systems. His expertise spans real-time architecture, algorithmic trading, market data, and risk management, with deep technical fluency in Java, Python, KDB+\/q, and AWS.<\/em><\/p>\n\n\n\n

Based in London, Jad is dedicated to designing robust systems under real-world constraints and mentoring the next generation of technologists.<\/em><\/p>\n\n\n\n

\u2026\u2026\u2026\u2026\u2026\u2026\u2026\u2026\u2026..<\/p>\n\n\n\n

Follow us on X<\/strong><\/a><\/p>\n\n\n\n

Follow us on LinkedIn<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Forecasting financial time series is one of the most complex tasks in data science. Q1. You\u2019ve been working in the Trading Tech and Quant Development space for the last 20+ years. What are the main lessons you\u2019ve learned through this experience?  Jad Sarmo: Back in 2004, I deployed the first automated trading system (ATS) for […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[1792,1794,1788,1791,1795,1790,1787,1793,1797,1789,1796],"_links":{"self":[{"href":"https:\/\/www.odbms.org\/blog\/wp-json\/wp\/v2\/posts\/5749"}],"collection":[{"href":"https:\/\/www.odbms.org\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.odbms.org\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.odbms.org\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.odbms.org\/blog\/wp-json\/wp\/v2\/comments?post=5749"}],"version-history":[{"count":15,"href":"https:\/\/www.odbms.org\/blog\/wp-json\/wp\/v2\/posts\/5749\/revisions"}],"predecessor-version":[{"id":5765,"href":"https:\/\/www.odbms.org\/blog\/wp-json\/wp\/v2\/posts\/5749\/revisions\/5765"}],"wp:attachment":[{"href":"https:\/\/www.odbms.org\/blog\/wp-json\/wp\/v2\/media?parent=5749"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.odbms.org\/blog\/wp-json\/wp\/v2\/categories?post=5749"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.odbms.org\/blog\/wp-json\/wp\/v2\/tags?post=5749"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}