New opportunity

Senior Quantitative Researcher | Crypto Delta One

BlockTech · Singapore

About this role

BlockTech is an algorithmic trading firm operating at the frontier of global crypto derivatives and spot markets. We are seeking a Senior Quantitative Researcher to join our trading floor and take ownership of research agendas from hypothesis to live PnL. Responsibilities: Own price-prediction, signal, execution, and anomaly-detection models across crypto markets using state-of-the-art ML. Collaborate with engineers to shape research, backtesting, and trading infrastructure. Monitor live model performance, diagnose decay, and iterate on production deployments. Set research direction alongside traders and mentor less experienced team members. Requirements: 4+ years of hands-on quantitative research and/or applied ML experience with a track record of models in production. Strong academic foundation in a quantitative discipline (mathematics, physics, statistics, computer science, ML/AI). Fluency in Python and the modern ML stack (PyTorch, TensorFlow, scikit-learn, NumPy, pandas). Deep understanding of overfitting, generalization, validation design, and feature engineering. Strong software engineering instincts for production-grade code. Excellent communication skills. Preferred qualifications: Live-trading track record in crypto derivatives or similar domains, experience mentoring researchers, and familiarity with market microstructure and derivatives pricing. Benefits: Competitive base salary with an attractive performance-based bonus plan, opportunity to buy into the trading fund, in-house training, learning & development budget, relocation package for internationals, and various office perks including meals and gym reimbursement.

For full details about this role, click “Apply on company site” to view the employer’s original posting.

Skills for this role

PythonPyTorchTensorFlowscikit-learnNumPypandasMachine LearningQuantitative ResearchAlgorithmic TradingFeature EngineeringBacktestingMarket MicrostructureDerivatives Pricing

Checking your profile…

Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.

Understand the role

What matters most

End-to-End Model Ownership
The role requires taking research from initial hypothesis through dataset construction, feature engineering, and training to live deployment and PnL monitoring. Success depends on the ability to manage the full lifecycle of models rather than focusing solely on theoretical research.
Production-Grade Engineering Standards
Candidates must demonstrate strong software engineering instincts. Because models must be integrated into trading infrastructure, code must be readable, testable, and robust enough for live production environments.
Cross-Functional Collaboration and Mentorship
The researcher must align with traders and engineers to set research direction while simultaneously raising the team's technical bar through mentorship and rigorous code/research reviews.
Rigorous Validation and Generalization
Given the volatility of crypto markets, the role prioritizes a deep, intuitive understanding of overfitting, validation design, and feature engineering to ensure models remain performant in live trading.

Likely challenges to think through

Managing Model Decay in High-Frequency Environments
Crypto markets are fast-moving and prone to rapid regime shifts. The challenge is diagnosing performance decay in real-time and iterating quickly. Prepare by discussing specific experiences where you identified and mitigated model drift in live production.
Balancing Research Agility with Infrastructure Constraints
There is a tension between the desire for rapid experimentation and the need for stable, safe production infrastructure. Prepare by highlighting how you have successfully collaborated with engineers to optimize backtesting pipelines without sacrificing research speed.
Prioritizing Research Bets Independently
As a senior researcher, you are expected to set your own agenda. The challenge is deciding which research paths are worth pursuing given limited time and capital. Prepare by explaining your framework for evaluating the expected value of a research hypothesis versus the cost of implementation.

Practice your answers

Technical practice

Handling Model Decay in Live Production

What to coverDescribe your process for monitoring live model performance and identifying when a model has begun to decay. Discuss how you distinguish between temporary market volatility and structural changes in market microstructure that require model retraining or feature adjustment.

Validation Design for Time-Series Data

What to coverExplain your approach to validation design in a financial time-series context to avoid look-ahead bias and overfitting. Suggestion: Focus on how you structure walk-forward validation or purged cross-validation to ensure your backtesting results are representative of live trading performance.

Feature Engineering for Crypto Microstructure

What to coverDiscuss how you construct features from high-frequency order book data or trade flow. Explain the trade-offs between using raw order book snapshots versus derived metrics like order flow imbalance or volatility measures.

Production-Grade Code Standards

What to coverWhat practices do you follow to ensure your research code is production-ready and maintainable by engineers? Address topics like modularity, unit testing for data pipelines, and documentation standards for complex ML models.

Derivatives Pricing and ML Integration

What to coverHow do you incorporate derivatives pricing theory into your machine learning models? Explain how you balance theoretical pricing models with data-driven signals to improve prediction accuracy in crypto derivatives markets.

Overfitting Mitigation Strategies

What to coverBeyond standard regularization techniques, how do you detect and mitigate overfitting when working with high-dimensional datasets? Suggestion: Discuss your philosophy on model complexity versus data availability and how you validate the robustness of your signals.

Infrastructure Collaboration

What to coverDescribe a scenario where you had to work with engineers to optimize a backtesting or execution pipeline. Explain how you communicated the technical requirements of your research to ensure the infrastructure supported your specific modeling needs.

Anomaly Detection in Trading

What to coverHow would you design an anomaly-detection model to identify unusual market behavior or execution errors? Discuss the choice of algorithms and how you define the threshold for what constitutes an actionable anomaly versus noise.

Behavioural practice

Prioritizing Research Agendas

What to coverDescribe a time you had to independently prioritize multiple research bets. Explain how you evaluated the potential PnL impact versus the time required to bring a model to production.

Mentorship and Technical Leadership

What to coverProvide an example of how you have mentored a less experienced researcher. Focus on how you helped them improve their technical rigor or their understanding of the end-to-end research lifecycle.

Cross-Functional Communication

What to coverTell me about a time you had to explain a complex model or research finding to a trader or engineer who did not share your technical background. How did you ensure alignment on the trading strategy?

Handling Failed Research Hypotheses

What to coverDescribe a situation where a promising research hypothesis failed to perform in backtesting or live trading. How did you diagnose the failure, and what did you learn about your research process?

Sharpen your knowledge

Topics to prepare

Model Generalization and Validation Design
The role requires a deep, intuitive grasp of overfitting and validation. Exercise: Design a robust walk-forward validation framework for a time-series signal, specifically addressing how to prevent look-ahead bias and handle non-stationary data distributions common in crypto markets.
Market Microstructure and Derivatives Pricing
Understanding how price is formed at the order-book level is a preferred qualification. Exercise: Review the mechanics of crypto perpetual swaps and order book dynamics, then draft a conceptual model for how limit order book imbalance can serve as a short-term predictive signal.

Skills to revise

Production-Grade Python Development
The role demands code that is readable, testable, and production-ready. Exercise: Refactor a research-grade script into a modular, unit-tested pipeline using object-oriented principles, ensuring clear separation between data ingestion, feature engineering, and model inference.
Feature Engineering for High-Frequency Data
You must own the end-to-end pipeline from raw data to model input. Exercise: Create a set of features derived from tick-level trade and quote data, focusing on capturing volatility and liquidity patterns, and evaluate their predictive power using scikit-learn metrics.
Model Monitoring and Decay Diagnosis
You will be responsible for models in production. Exercise: Develop a diagnostic dashboard or script that tracks feature drift and model performance metrics (e.g., Sharpe ratio, RMSE) over time to identify when a model requires retraining or adjustment.

Your preparation checklist

Prepare a structured research project walkthrough
Select a past project where you took a model from hypothesis to production. Be prepared to discuss your specific role in dataset construction, feature engineering, and the rationale behind your model architecture. Focus on how you handled overfitting and validation design in a live trading context.
Document your production-grade coding standards
Review your Python code repositories to ensure they demonstrate clean, modular, and testable practices. Be ready to explain how you collaborate with engineers to transition research code into production-ready infrastructure, emphasizing performance and reliability.
Refine your technical narrative on model decay
Prepare concrete examples of how you have monitored live model performance, identified signs of decay, and executed iterative improvements. This should highlight your ability to diagnose issues in real-time and your systematic approach to model maintenance.
Develop insights on crypto market microstructure
Formulate thoughtful questions regarding the specific crypto derivatives or spot market venues BlockTech trades on. Research common microstructure challenges in these markets and be prepared to discuss how you would approach pricing or anomaly detection in high-frequency environments.
Articulate your approach to research leadership and mentorship
Prepare examples of how you have mentored junior researchers or influenced team standards. Be ready to discuss your philosophy on setting research agendas and how you balance independent research bets with collaborative team goals.

Availability last checked: 18 Oct 2026. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy

KEEP EXPLORING

Similar AI jobs

Related skills and specializations in Singapore. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…