AI/ML Engineer - Financial Prediction & Quant Intelligence

Full Description

Requirements:

Strong proficiency in Python, PyTorch or TensorFlow.

Hands on experience in NLP, ML, time series forecasting, and computer vision.

Solid understanding of financial markets, macroeconomic indicators, and technical analysis.

Experience building end to end ML pipelines and deploying models to production.

Familiarity with MLOps tools (MLflow, W&B), Docker, FastAPI, and cloud environments.

Background in fintech, algorithmic trading, or financial analytics.

Experience with LLMs, embeddings, RAG pipelines, and transformer architectures.

Knowledge of backtesting frameworks (Backtrader, Zipline, or custom engines).

Experience with distributed computing (Spark, Ray).

Responsibilities:

Develop linear and data driven forecasting models for macroeconomic indicators (GDP, CPI, employment).

Build predictive models for on chain metrics, DVOL, volatility indices, and other market signals.

Design data settled forecasting instruments for expectation based trading.

Collaborate with product and engineering teams to integrate models into production systems.

Create rule based and ML driven technical indicators for short and mid term trading strategies.

Build ML models for pattern recognition, volatility regime detection, and microstructure analysis.

Conduct backtesting, feature engineering, and model optimization.

Work closely with traders and analysts to convert signals into actionable insights.

Develop financial NLP models (FinBERT style, transformer based, LLM based) for real time sentiment scoring.

Build systems to evaluate market impact of news, economic releases, and social media signals.

Design pipelines for ingestion, cleaning, ranking, and scoring of text based financial data.

Integrate sentiment signals into trading and forecasting models.

Apply computer vision techniques to analyze candlestick charts, indicators, and visual market patterns. Build CNN/ViT based models to detect technical patterns (breakouts, divergences, head & shoulders, etc.).

Convert chart images into structured features for ML and quant models.

Work with data engineering teams to generate and maintain chart based datasets.