Keuro Life

Job Title : AI Engineer - LLMsLocation : ChennaiCompany : Keuro DigitalExperience Required : 5+ years overall, with at least 2 years of hands-on experience in LLMsAbout Keuro Digital : Keuro Digital is a forward-thinking digital technology company driving innovation across healthcare, pharma, and consumer tech. We are building intelligent, scalable solutions that harness the power of AI to transform user experiences, operational efficiency, and business impact.Role Overview : We are looking for an experienced AI Engineer with a strong foundation in Large Language Models (LLMs) to join our growing AI/ML team. You will play a pivotal role in designing, fine-tuning, and deploying high-scale, LLM-powered applications. Youll work with state-of-the-art models (e.g., GPT, Gemini, LLaMA, etc.), build scalable NLP pipelines, and productionize intelligent systems for real-world impact.Key Responsibilities :- Design, train, and fine-tune LLMs for specific business applications using open-source and proprietary models.- Build and scale NLP pipelines for text generation, summarization, classification, Q&A, and semantic search.- Develop and implement Retrieval-Augmented Generation (RAG) systems using vector databases.- Integrate LLM-based solutions into production environments ensuring scalability, performance, and reliability.- Optimize inference performance of large models for real-time applications.- Collaborate with data scientists, product managers, and backend engineers to deliver intelligent features end-to-end.- Leverage prompt engineering and custom adapters (LoRA, PEFT, etc.) for model tuning and efficiency.- Maintain reproducible ML workflows using MLOps tools and CI/CD practices.Required Skills & Qualifications :- 5+ years of total experience in software/ML engineering with at least 2 years in LLMs/NLP applications.- Proficiency in Python and hands-on experience with ML/DL frameworks such as PyTorch or TensorFlow.- Deep understanding of transformer architectures and modern LLMs (GPT, LLaMA, Claude, Gemini, etc.).- Experience with prompt engineering, fine-tuning, or instruction tuning.- Practical experience with RAG pipelines, embedding models, and vector databases like FAISS, Pinecone, or Weaviate.- Experience deploying LLM applications in production at scale (preferably on cloud platforms like AWS, Azure, or GCP).- Familiarity with containerization (Docker), API integration (FastAPI/Flask), and model serving.- Working knowledge of MLOps tools (MLflow, Weights & Biases, etc.) is a plus.Nice to Have :- Experience with open-source LLMs and distributed training (Deepspeed, Hugging Face Accelerate).- Understanding of privacy, security, and ethical AI deployment.- Exposure to LangChain, Haystack, or similar LLM orchestration frameworks.Why Keuro Digital?- Work at the cutting edge of LLMs and generative AI.- Collaborate with a global, cross-functional team.- Opportunity to impact healthcare and pharma sectors through meaningful AI-driven innovations.- Fast-paced, product-first culture with room for experimentation and ownership. (ref:hirist.tech)