Senior AI​/ML Engineer

At LegitScript, we are passionate about making the internet and payment ecosystems safer and more transparent. We help companies of all sizes keep their services legal and safe for consumers. To do this, LegitScript combines big data with the world’s leading team of experts skilled in highly regulated and complex sectors, including transaction laundering detection, pharmaceuticals, online gambling, and more.

The result? Unmatched accuracy and deep risk analysis that identifies which commercial entities play by the rules, and which do not. Our diverse industry partnerships provide unique insights that keep businesses and governments at the forefront of emerging trends. That’s why LegitScript is trusted by the world's largest search engines, internet platforms, payment companies, and regulatory agencies.

We’re an innovative technology incubator seeking an experienced and forward-thinking Senior AI/ML Engineer specializing in Generative AI to join our team. In this role, you’ll spearhead the development and implementation of cutting‑edge AI solutions, with a primary focus on creating a sophisticated risk detection algorithm using large language models, Generative AI techniques, and traditional machine learning methods within our SaaS environment.

• Implement and optimize AI orchestration frameworks like crew
  
  AI and Lang Chain to manage complex, multi‑agent AI workflows and improve task delegation efficiency.
• Develop and maintain a comprehensive testing pipeline using industry‑standard tools for experiment tracking, model versioning, and performance visualization.
• Design and execute A/B tests for prompt engineering, comparing different versions to maximize output quality and consistency.
• Establish best practices for prompt templating, version control, and documentation to ensure scalability and maintainability of AI systems.
• Develop a robust evaluation framework for assessing AI model outputs, including automated metrics and human‑in‑the‑loop feedback mechanisms.
• Implement prompt chaining and reasoning techniques to break down complex tasks into manageable sub‑tasks for improved accuracy and explainability.
• Create and maintain a knowledge base of effective prompting techniques, including examples and case studies, to facilitate team learning and consistency.
• Develop strategies for handling edge cases and out‑of‑distribution inputs, including fallback mechanisms and graceful degradation of AI system performance.
• Integrate AI systems seamlessly with the existing backend and frontend stack, ensuring full‑stack implementation and optimization of AI features within the application architecture.

• Familiarity with Large Language Models, Transformers, Vector Embeddings, and other Generative AI techniques in a SaaS environment.
• Strong foundation in Traditional Machine Learning approaches.
• Experience with COTS Generative AI solutions.
• Experience with Weights and Biases platform for measuring and tuning as it relates to Generative AI.
• Strong hands‑on experience with MLFlow (Databricks MLFlow experience is a plus).
• Exposure to Mosaic AI (Agents and Vector Search).
• Expertise with Spark/PySpark for large‑scale data processing.
• Proficiency in Python, with practical experience using PyTorch, Tensor Flow, and Scikit‑learn for building and deploying models.
• Familiarity with MLOps principles, tools, and workflows for scalable and reliable ML deployment.
• Ability to quickly create Proof‑of‑Concept code and engage with multiple stakeholders to drive PoC productization.
• A customer‑centric approach and a relentless drive for excellence, aligned with our foundational values.
• Exceptional written and verbal communication skills, capable of inspiring and engaging others.
• Self‑motivation, integrity, and a track record of delivering impactful results with a high degree of autonomy.
• Agility and adaptability to thrive in fast‑paced work environments.
• A degree in computer science or a related field, with a preference for advanced qualifications.

• Familiarity with Databricks Features for production workflows.
• Knowledge of Model Serving Endpoints for deploying ML models at scale.
• Experience with…