Job Opportunity: LLM Engineer at Qure.AI

Qure.AI is seeking a talented LLM Engineer to significantly advance our generative AI roadmap. This role focuses on building scalable, production-grade systems that leverage large language models (LLMs) within healthcare workflows. You will be responsible for the end-to-end application of LLMs, extending beyond prompt design to include architecting internal tools and APIs, and ensuring robust performance, usability, and compliance in real-world deployments. If you are passionate about developing the foundational technology to ensure reliable LLM performance in critical healthcare settings, we encourage you to apply.

Key Responsibilities

• Design and implement LLM-based features for Qure's products, including clinician-facing assistants and automated diagnostic workflows.
• Develop internal tools, APIs, and developer utilities to facilitate scalable LLM integrations.
• Collaborate with prompt engineers to create modular and composable workflows, such as Retrieval-Augmented Generation (RAG), chaining, and structured prompting.
• Evaluate model performance and behavior across various tasks, utilizing both human feedback and automated metrics.
• Optimize LLM systems for latency, cost, and reliability through caching, batching, and fallback strategies.
• Deploy and monitor LLM services in production, integrating observability and usage analytics.
• Build systems for managing prompt versions, LLM configurations, and multi-model experimentation.
• Lead cross-functional initiatives and drive end-to-end project execution involving engineering, product, and clinical teams.
• Contribute to internal guidelines for LLMs, safety practices, and developer enablement.
• Promote a culture of collaboration, ownership, and technical excellence in developing impactful LLM-driven solutions.

Required Skills and Qualifications

• Bachelor's degree in Computer Science, Information Technology, or a related field.
• Strong understanding of LLM architectures, inference workflows, context management, and prompt patterns.
• Proficiency in Python programming, with familiarity in frameworks such as LangChain, Haystack, or Pydantic AI.
• Experience integrating models from OpenAI, Anthropic, or open-source alternatives into production systems.
• Familiarity with emerging LLM protocols like MCP and frameworks enabling agentic behaviors, including autonomous agents, task decomposition, and memory systems.
• Demonstrated ability to collaborate effectively across infrastructure, product, and research teams.
• Comfort with cloud platforms (AWS/GCP), containerized deployments (Docker/Kubernetes), and observability tools.
• Solid understanding of implementing guardrails for LLMs to ensure responsible, safe, and reliable production usage.
• Excellent problem-solving, communication, and cross-functional collaboration skills.

Preferred Skills

• Experience in the healthcare industry, with an understanding of relevant compliance and security requirements.
• Experience building user-facing tools or assistants powered by LLMs.
• A strong sense of ownership and the ability to balance experimentation with production readiness.
• Familiarity with agile methodologies and project management practices.