Senior AI/LLM Engineer (Python)

• Prompt Design & Optimization – Craft, test, and refine advanced prompts for LLM agents to optimize accuracy, tone, task execution, and user satisfaction
• LLM Performance Tuning – Develop evaluation criteria and benchmarking workflows to assess and continuously improve prompt effectiveness
• Experimentation at Scale – Utilize tools like Langsmith, promptfoo, or Langfuse to run experiments and manage prompt versioning
• Deploy to Production – Collaborate with engineers, QA, and product teams to integrate LLM prompts into voicebots/agents supporting customer care
• Iterate on Feedback – Use telemetry, agent logs, and user data to identify improvement opportunities and tune prompts accordingly
• Stay Ahead of the Curve – Research new prompting frameworks, emerging techniques (e.g., ReAct, CoT), and GenAI tooling

• Excellent English Proficiency – Precision in language, strong written/verbal skills, and attention to tone, nuance, and clarity
• LLM Expertise – Deep understanding of prompt engineering, large language model behaviors, and conversational context management
• Production Experience – 1+ year of real-world prompt engineering for chatbots/voicebots serving live users
• LangSmith & LLM Tooling – Proficiency with LangSmith or similar platforms (e.g., promptfoo, Langfuse, Arize Phoenix) for evaluating, debugging, and monitoring LLM applications
• Problem Solver – Analytical mindset with a knack for debugging prompt failures and improving user experience
• AI Enthusiasm – Passion for GenAI, LLMs, and their potential; constantly learning and experimenting

Nice to Have:

• Familiarity with customer service workflows or home services domain
• Experience designing prompts for multi-turn conversations and agent-like behavior