SDE - III, LLM

Job Summary

Location: Bangalore, India

Experience: 2-5yrs

Type: Full Time

Department: Engineering

The Opportunity

We are looking for an LLM Engineer to accelerate our generative AI roadmap by building scalable, production-grade systems that leverage large language models across healthcare workflows. This role goes beyond prompt design, you own the end-to-end application of LLMs, from architecting internal tools and APIs to ensuring robust performance, usability, and compliance in real-world deployments.

What You Own & Drive

• Design and implement LLM-based features across Qures products, from clinician-facing assistants to automated diagnostic flows.
• Build internal tools, APIs, and developer-facing utilities to enable scalable LLM integrations.
• Collaborate with prompt engineers to design modular, composable workflows (e.g., RAG, chaining, structured prompting).
• Evaluate model performance and behavior across tasks using both human feedback and automated metrics.
• Optimize latency, cost, and reliability of LLM systems using caching, batching, and fallback strategies.
• Deploy and monitor LLM services in production, integrating observability and usage analytics.
• Build systems to manage prompt versioning, LLM configurations, and multi-model experimentation.
• Lead cross-functional initiatives and drive end-to-end project execution across engineering, product, and clinical teams.
• Contribute to internal LLM guidelines, safety practices, and developer enablement.
• Foster a culture of collaboration, ownership, and technical excellence in building impactful LLM-driven solutions.

Core Skills Required

• Bachelors degree in Computer Science, Information Technology, or a related field.
• Solid understanding of LLM architectures, inference workflows, context management, and prompt patterns.
• Strong programming skills in Python, familiarity with frameworks like LangChain, Haystack, or Pydantic AI.
• Experience integrating OpenAI, Anthropic, or open-source models into production systems.
• Familiarity with emerging LLM protocols such as MCP and frameworks that enable agentic behaviours (e.g., autonomous agents, task decomposition, memory systems)
• Proven ability to work across infra, product, and research teams.
• Comfort with cloud platforms (AWS/GCP), containerized deployments (Docker/K8s), and observability tools.
• Solid understanding of how to set up guardrails around LLMs to ensure responsible, safe, and reliable usage in production systems.
• Strong problem-solving, communication, and cross-functional collaboration skills.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.