Senior Data Scientist

Direct message the job poster from Hytech Global Talent Partner - MENA, APAC, UK, EU About Hytech Hytech is a leading management consulting firm headquartered in Australia and Singapore, specializing in digital transformation for fintech and financial services companies. We provide comprehensive consulting solutions, as well as middle- and back-office support, to empower our clients with streamlined operations and cutting-edge strategies. Our key clients include top trading platforms and cryptocurrency exchanges. With a global team of over 2,000 professionals, Hytech has established a strong presence worldwide, with offices in Australia, Singapore, Malaysia, Taiwan, Philippines, Thailand, Morocco, Cyprus, and more. You'll join our Singapore hub, working closely with Quants, Data Scientists, and Risk Analysis team (RA) on a high-impact production system. The Opportunity: Drive the ML/DL research agenda for our client-classification engine and adjacent transaction risk control/anti-fraud scenarios across the trading chain . Take the best ideas to production—safely, fast, and cost-effectively. You'll own the end-to-end experiment loop, from hypothesis → backtest → calibration → monitored rollout , so our routing and control decisions improve broker P&L, stability, and abuse prevention . What you'll do: Be the key owner for modeling research execution for client classification and related risk/anti-fraud checks; frame hypotheses with Quants, align labels with RA, and run clean, time-aware evaluations. Broaden scope to risk/anti-fraud : apply the above methods to sibling controls along the transaction chain (toxic-flow & scalping patterns, slippage anomalies, stop-out risk, collusion/copy-trading, funding-rate/credit abuse, withdrawal risk); prioritize by expected P&L and operational impact. Own the experiment loop end-to-end (hypothesis → backtest → thresholding/calibration → monitored rollout) with MLflow tracking and clear readouts. Optimize for business impact : tune decisions for net P&L, and FP$/FN$; make trade-offs explicit (accuracy vs. latency/cost). Ship safely to production : shadow tests, canary releases, rollback plans, and lightweight guardrails aligned with risk policy. Keep models healthy : monitor drift, label delays, and calibration; set retrain triggers and maintain a steady weekly iteration cadence with Quants/RA. Communicate clearly : short design docs, experiment summaries, and release notes that non-ML stakeholders can act on. Time-series modeling of order streams : comfortable prototyping and comparing simple sequence models (e.g., an LSTM or a light Transformer) against straightforward baselines; pick the simplest approach that moves the metric. Practical representation learning : able to learn compact client/strategy embeddings to improve cold-start and data efficiency (e.g., a basic autoencoder or simple contrastive objective) without overcomplicating the stack. Working with imperfect labels : experience basic approaches for partial/noisy labels—e.g., positive-unlabeled setups or simple denoising checks, so models stay robust. Policy impact & efficient iteration : estimate offline impact of routing decisions with lightweight methods; run small, well-instrumented HPO jobs (e.g., Optuna/Hyperopt) and keep costs/latency in check. Uncertainty & deferral : provide calibrated scores with simple confidence/deferral logic; when unsure, safely fall back to rules or RA review. 5+ years owning ML systems end-to-end with a track record of modeling research → production impact on large tabular/time-series problems. Strong PySpark/Spark SQL on Databricks and Python; excellent command of MLflow (or equivalent) , model registries, CI/CD, and jobs-as-code. Proven skill in experimental design : temporal cross-validation, leakage prevention, out-of-time backtests, label-delay handling, and calibration/thresholding. Comfortable optimizing for asymmetric costs and communicating trade-offs (precision/recall vs. P&L, latency vs. accuracy) to non-ML stakeholders. Clear, concise writing; able to own RFCs and implementation plans. Domain exposure to brokerage/CFD/FX/crypto routing, hedging, or dealer risk. Experience with partially labeled or noisy-label settings , active feedback loops, and production A/B or shadow testing. Practical interpretability for stakeholder trust and release gating. Tech you'll use Seniority level: Mid-Senior level Employment type: Full-time Job function: Information Technology Industries: Desktop Computing Software Products, IT System Custom Software Development, and Securities and Commodity Exchanges We're removing boilerplate references and ensuring the description focuses on role responsibilities and qualifications. #J-18808-Ljbffr