Description

You will validate and improve the accuracy of LLM-powered agents in Capital Markets applications.

This role is hybrid.

Responsibilities

• Test and validate AI agent responses to identify hallucinations, misinterpretations, and inconsistencies.
• Fine-tune AI agent outputs based on validation findings and curated data inputs.
• Ensure generated content remains relevant and reliable for Capital Markets use cases.
• Validate agent outputs against trusted sources to maintain data integrity.

Required Skills

• 5+ years of professional software or quality engineering experience.
• Proficiency in LLM fine-tuning practices and GenAI principles.
• Hands-on experience with OpenAI and Anthropic ecosystems.
• Strong understanding of Capital Markets domains (trading, risk, compliance, research, structured products).
• Experience using Snowflake for data validation.
• Experience using Databricks for data processing.

Key Skills

Education

Any Gradute