Algorithmic Developer – Provably Fair & RNG Systems

About the Project:
We are seeking an experienced Developer / Machine Learning Engineer with deep expertise in Random Number Generation (RNG) algorithms and Provably Fair architectures. The goal of this project is to analyze, optimize, and potentially rebuild our current predictive/analytical model pipeline.

Currently, we have an active LSTM-based model setup. We need an expert who can evaluate its architecture, improve its accuracy and efficiency, or design superior alternative models from scratch tailored to our specific data distribution and fairness requirements.

Key Responsibilities:

Audit and optimize the existing LSTM model pipeline for better performance and predictive accuracy.

Evaluate alternative architecture options (e.g., Transformers, Markov models, or hybrid architectures) and build new models from scratch if required.

Ensure all algorithmic logic strictly aligns with RNG principles and Provably Fair cryptographic standards (HMAC, SHA-256 / SHA-512 verification).

Fine-tune hyperparameters, validate data pipelines, and reduce model latency.

Requirements:

Proven track record working with RNG (Random Number Generation) and Provably Fair frameworks in production environments.

Deep experience in Time-Series Forecasting and Sequential Data Modeling using LSTM, GRU, or Attention/Transformer networks.

Strong background in PyTorch or TensorFlow.

Solid understanding of cryptography basics relevant to Provably Fair verification mechanisms.