LLM Engineer

Overview

• Design and implement LLM-powered features across product suite.
• Build internal tools, APIs, and utilities for scalable LLM integration.
• Collaborate with prompt engineers on modular workflows (RAG, chaining, structured prompting).
• Evaluate model performance using human feedback and automated metrics.
• Optimize system latency, cost, and reliability (caching, batching, fallbacks).
• Deploy and monitor LLM services with full observability and analytics.
• Manage prompt versioning, model configs, and multi-model experimentation.
• Lead cross-functional projects across engineering, product, and clinical teams.
• Develop LLM safety guidelines and internal best practices.
• Champion a culture of technical excellence and collaboration.

Required Skills

• Bachelor's in CS/IT or related field
• Strong understanding of LLM architectures, inference workflows, and prompt engineering patterns
• Proficiency in Python; experience with LangChain/Haystack/Pydantic AI
• Experience working with OpenAI, Anthropic, or open-source models in production
• Familiarity with MCP and agentic frameworks (autonomous agents, memory systems, decomposition)
• Experience across infra, product, and research teams
• Cloud expertise (AWS/GCP), Docker/K8s, and observability tools