
Lead Engineer, AI Platform
Posted 3 days ago

Posted 3 days ago
This is a fully remote position, open to applicants in Europe.
• Develop and oversee evaluation infrastructure, encompassing CI/CD pipelines, scoring systems, and datasets for Circle’s AI agents.
• Identify and troubleshoot failures throughout the agent pipeline, which includes planning, execution, tool selection, and trajectories.
• Transform diagnostic insights into prototypes or priorities for the AI Core engineering team.
• Create annotation workflows and generate AI-produced and simulated conversations for evaluation datasets.
• Conduct structured experiments on prompts, models, and the agent harness.
• Assess new and open-source models in comparison to production baselines.
• Construct frameworks for model-shift decisions and enhance cost-effectiveness and latency through model swaps, caching, and routing.
• Lead and guide the AI Quality engineering team while remaining actively involved in coding.
• Define technical direction and oversee daily priorities.
• Collaborate with AI Core engineering to confirm quality enhancements.
• Over 7 years of experience in developing and deploying production software, preferably including LLM-powered agents that perform real actions within a product.
• Familiarity with complex, tool-utilizing systems, which involve multiple tools, planning or orchestration, and sub-agents.
• Proficient in Ruby on Rails / Python or willing to learn them rapidly.
• Strong proficiency in Python is highly advantageous, particularly for data and evaluation tasks.
• Experience in creating evaluation or observability infrastructure for ML/AI systems.
• Knowledge of evaluation frameworks such as Braintrust, LangSmith, or similar tools.
• Experience in designing datasets, annotation workflows, or labeling pipelines for ML/AI evaluation.
• Quick learner, willing to experiment, and able to thrive in a fast-paced, dynamic environment.
• Comfortable working amidst ambiguity in a high-speed setting.
• Strong alignment with company values.
• Fluent in English, both spoken and written, at CEFR Level C2 / ILR Level 5.
• Equity in the company with ongoing refresh grants.
• 35 days of paid time off annually.
• Remote-only work arrangements with flexibility and autonomy.
• Company retreats held twice a year in amazing locations around the globe.
• Comprehensive benefits package that supports health, wellbeing, and professional development.
datavent.io
Machinify
Get handpicked remote jobs straight to your inbox weekly.