Machine Learning Engineer – LLM Evaluation & Automation

Grid Dynamics is a leading provider of technology consulting and advanced analytics services, and they are seeking a highly skilled Machine Learning Engineer specializing in Large Language Models for automated evaluation and quality assessment. The role involves designing systems to measure and improve model outputs, leading initiatives for evaluation pipelines, and collaborating with cross-functional teams to enhance product reliability and user experience.

Responsibilities:

• Design and implement automated systems and pipelines for evaluating LLM outputs
• Develop metrics and KPIs to measure output quality, accuracy, and consistency using LLM-based evaluations
• Collaborate with Engineering teams to create automated logic checks and validation tools
• Partner with Data Scientists to analyze evaluation results and optimize prompt and task structures
• Provide feedback loops to ensure evaluation guidelines align with LLM-based assessments
• Investigate how LLM-derived evaluations can enhance product reliability and user experience
• Recommend refinements to prompt engineering, evaluation strategies, and automation tools
• Stay informed on emerging trends in LLM evaluation, automated quality assessment, and AI toolchains
• Continuously improve and expand automated evaluation processes based on industry best practices

Requirements:

• 5+ years of experience in ML engineering, NLP, or AI/ML automation
• Advanced degree (MS/PhD) in Statistics, Data Science, Computational Social Science, Quantitative Psychology, or a related field
• Strong understanding of machine learning principles with focus on NLP and advanced LLM capabilities (e.g., Chain-of-Thought, agentic workflows)
• Expertise in building automated evaluation or QA pipelines
• Excellent analytical and problem-solving skills with experience in root cause and error pattern analysis
• Proven project management and cross-functional collaboration experience
• Excellent communication skills to convey complex insights to technical and non-technical audiences
• Detail-oriented mindset with a focus on evaluation metrics, prompt design, and automation
• Ability to quickly adapt to new business rules and evaluation guidelines across diverse product domains
• Strong programming skills in Python and SQL
• Hands-on experience in prompt engineering and designing LLM-based evaluation systems
• Experience with big data technologies like PySpark for data aggregation and sampling