Qure.ai•2h ago
InstaHyre
LLM Engineer
Bangalore
Full Time
Mid Level
N/A
N/A
N/A
Responsibilities
Qualifications & Requirements
Experience Level: Mid Level
Full Job Description
Qure.ai is seeking an LLM Engineer to drive our generative AI initiatives by building scalable, production-ready systems that integrate large language models into healthcare workflows. This role involves end-to-end ownership of LLM applications, from architecting internal tools and APIs to ensuring performance, usability, and compliance in real-world healthcare settings. If you are passionate about developing foundational technologies for reliable LLM deployment in critical environments, we encourage you to apply.
Responsibilities
- Develop and deploy LLM-powered features within Qure's product suite, including clinician support tools and automated diagnostic processes.
- Construct internal utilities, APIs, and developer resources to facilitate scalable LLM integrations.
- Collaborate with prompt engineers to create modular and composable LLM workflows, such as Retrieval-Augmented Generation (RAG), chaining, and structured prompting.
- Assess LLM performance and behavior through human feedback and automated metrics.
- Optimize LLM system latency, cost, and reliability using techniques like caching, batching, and fallback mechanisms.
- Manage the deployment and monitoring of LLM services in production, incorporating observability and usage analytics.
- Implement systems for prompt version control, LLM configuration management, and multi-model experimentation.
- Lead cross-functional projects, ensuring successful execution across engineering, product, and clinical teams.
- Contribute to the establishment of internal LLM best practices, safety guidelines, and developer enablement programs.
- Promote a collaborative environment focused on ownership and technical excellence to deliver impactful LLM-driven solutions.
Requirements
- Bachelor's degree in Computer Science, Information Technology, or a related discipline.
- Comprehensive understanding of LLM architectures, inference processes, context management, and prompt engineering techniques.
- Proficiency in Python programming and familiarity with frameworks such as LangChain, Haystack, or Pydantic AI.
- Demonstrated experience integrating models from OpenAI, Anthropic, or open-source alternatives into production environments.
- Familiarity with emerging LLM protocols like MCP and agentic behavior frameworks (e.g., autonomous agents, task decomposition, memory systems).
- Proven ability to collaborate effectively across infrastructure, product, and research teams.
- Experience with cloud platforms (AWS/GCP), containerization technologies (Docker/Kubernetes), and observability tools.
- A strong grasp of implementing guardrails for LLMs to ensure safe, responsible, and reliable production usage.
- Excellent problem-solving, communication, and cross-functional collaboration skills.
Preferred Skills
- Experience within the healthcare industry, including an understanding of compliance and security mandates.
- Experience developing user-facing tools or assistants powered by LLMs.
- A strong sense of ownership and the ability to balance innovative experimentation with production-readiness.
- Familiarity with Agile methodologies and project management best practices.
Company
Qure.ai
Qure.ai specializes in developing cutting-edge deep learning products and platforms for clinical radiology diagnostics. Our expert team blends clinical acumen with deep learning proficiency, supported...
Bangalore
Posted on InstaHyre