Applied LLM Engineer – AI Voice & Automation Platform

About the Company

• Our client is an innovative technology startup building cutting-edge voice automation solutions for enterprise teams. Their mission is to make it effortless for businesses to create AI-powered phone and voice agents that deliver natural, human-like conversations at scale - without complex coding or heavy infrastructure. They’re a fast-growing company in the AI space, focused on applied research, performance, and real product impact.

About the Role

• We’re seeking an Applied LLM Engineer who thrives at the intersection of large language models, prompt engineering, and robust backend development. In this role, you’ll work closely with customers and internal teams to design, refine, and deploy models that drive measurable improvements in AI agent performance. You’ll turn real-world conversational data into better prompts, evaluation pipelines, and production-ready enhancements.

Key Responsibilities

• Develop and iterate on prompt frameworks and system/tooling logic to improve model quality and conversational outcomes.
• Collaborate with customer teams to gather feedback and translate that into actionable improvements.
• Build production-grade Python services, APIs, and evaluation tools to support LLM-driven applications.
• Design experiments, collect labelled data, and manage A/B testing to track model performance.
• Work hands-on with major LLM APIs and ensure stable, scalable integrations across systems.
• Maintain strong data hygiene practices, including compliance with privacy and PII standards.

Who You Are

• 3+ years of experience coding in Python, with strong focus on clean, tested, production-quality code (typing, pytest, profiling).
• Proven track record in Prompt Engineering - including system prompts, meta-prompting, and iterative tuning.
• Hands-on experience integrating with leading LLM APIs (OpenAI, Anthropic, Google, Mistral, etc.).
• Strong evaluation mindset, able to define success metrics and run structured experiments.
• Excellent communication and product intuition, comfortable translating feedback into deployed improvements.
• Familiarity with small backend services (FastAPI preferred) and data management practices.