Technical Lead (IN)
HCLTech
HCLTech
This role focuses on engineering large language model (LLM) solutions, transforming their capabilities into reliable, scalable, and secure enterprise applications. The goal is continuous improvement based on performance, cost, and user feedback.
Design and develop LLM-powered applications using both proprietary and open-source models. Implement advanced techniques like prompt engineering, Retrieval-Augmented Generation (RAG), tool/function calling, and agent workflows. Deploy LLM solutions with scalability and reliability in cloud and enterprise settings. Build inference APIs, microservices, and CI/CD pipelines for AI applications. Monitor production models for quality, latency, cost, drift, and hallucinations. Fine-tune models using parameter-efficient methods and optimize inference performance through caching, batching, quantization, and prompt optimization. Ensure security, privacy, and responsible AI principles are upheld in all deployments. Collaborate cross-functionally with product, platform, and engineering teams to deliver comprehensive enterprise AI solutions.
Requires strong Python programming skills and experience with backend APIs. Hands-on experience with LLM frameworks such as LangChain or LlamaIndex is essential. Proficiency in building RAG pipelines using vector databases is necessary. Familiarity with Docker, Kubernetes, cloud platforms, and CI/CD pipelines is expected. Knowledge of LLMOps/MLOps tools and monitoring systems is also required. The role demands 5-7 years of overall software or ML engineering experience, with at least 1-3 years specifically focused on delivering LLM or Generative AI solutions in a production environment.
HCLTech
IT Consulting