Lead Prompt Engineer

Key responsibilities

• Lead the design and development of effective prompts for AI models, focusing on applications within equity trading, real-time order monitoring, and advanced analytics.
• Utilize

  KDB+

  and q for processing and analyzing high-volume, high-frequency time-series data streams from sources like market feeds, facilitating actionable insights.
• Collaborate with traders, quants, and analysts to understand business requirements and translate them into robust prompt engineering solutions for real-time order monitoring, trade reconciliation, and portfolio attribution analysis.
• Design prompts for tasks such as data cleaning, transformation, automated reconciliation, and report generation and analysis within investment operations.
• Optimize prompt performance, refine prompt logic, and troubleshoot issues to ensure accurate, relevant, and timely outputs from AI systems.
• Develop systematic prompt evaluation methodologies and establish best practices for prompt creation, documentation, and version control.
• Stay abreast of advancements in large language models (

  LLMs

  ), prompt engineering techniques, AI/machine learning frameworks, and their potential application in financial markets.
• Ensure prompt design and AI outputs adhere to regulatory and compliance requirements within the financial industry.

Required skills and qualifications

• 9+ years

  of hands-on experience in prompt engineering, with a strong focus on real-time applications.
• Deep expertise in

  KDB+

  development and q programming, including designing and implementing KDB+ architectures, and scaling systems in production environments.
• Proven track record in developing and optimizing prompt engineering solutions for complex workflows, ideally within equity trading, order monitoring, and analytics.
• Proficiency in programming languages like Python, with experience in AI/machine learning frameworks (e.g., TensorFlow, PyTorch).
• Strong understanding of Natural Language Processing (NLP) and Large Language Models (LLMs), including techniques like few-shot learning and chain-of-thought prompting.
• Experience in integrating AI models with external data sources and tools, including API scripting and vector embedding integration for retrieval-augmented generation (RAG).
• Demonstrated technical leadership, problem-solving abilities, and decision-making in fast-paced projects.
• Excellent communication skills, both written and verbal, capable of explaining complex systems to technical and non-technical stakeholders.

Experience in capital markets or investment banking, with an understanding of financial instruments and market dynamics.