Responsibilities
- Develop and enhance AI systems using large language models and custom machine learning solutions for production environments.
- Design and manage full lifecycle ML and LLM pipelines, from initial prototypes to deployment and ongoing monitoring.
- Write clean, efficient, and maintainable Python code that supports testing and long-term scalability.
- Enhance evaluation frameworks, system observability, and performance tracking for AI services, focusing on quality, speed, reliability, and cost-efficiency.
- Collaborate with product managers, platform engineers, and other teams to deliver AI-driven features.
- Analyze current implementations to detect inefficiencies, defects, and areas for performance improvement.
- Design and execute controlled experiments to evaluate AI features and derive meaningful insights from data.
- Participate in technical design discussions and code reviews to elevate team-wide engineering standards.
- Iterate on model behavior, prompting techniques, retrieval methods, tool integration, and workflow orchestration to improve user results.
