?

Experience:
5+ Years ? Work Mode: As per business requirements We are looking for an experienced LLM Engineer with strong expertise in Large Language Models, Python, Generative AI, LLM fine-tuning, model optimization, and deployment. The ideal candidate will be responsible for developing, fine-tuning, optimizing, and deploying LLM-powered applications and enterprise-grade AI solutions. ?

Key Responsibilities
• Design, develop, and deploy LLM-based applications and Generative AI solutions.
• Work with large language models such as OpenAI GPT, Google Gemini, Anthropic Claude, Llama, Mistral, or similar.
• Implement model fine-tuning, customization, and optimization techniques for specific business use cases.
• Work on LLM training, inference, evaluation, and deployment workflows.
• Implement techniques such as LoRA, QLoRA, PEFT, and quantization for model optimization.
• Develop prompt engineering strategies and optimize model responses for accuracy and relevance.
• Build RAG-based applications using embeddings, semantic search, and vector databases.
• Develop scalable APIs and integrate LLMs with enterprise applications and backend systems.
• Optimize LLM inference performance, latency, throughput, and resource utilization.




• Implement LLM evaluation, testing, monitoring, and observability frameworks.
• Ensure responsible AI practices, data security, and hallucination mitigation.
• Collaborate with data scientists, AI architects, and engineering teams to deliver production-ready AI solutions. ? Mandatory

Skills:
• 5+ years of experience in AI/ML, NLP, or software engineering with relevant LLM development experience.
• Strong programming expertise in Python.
• Hands-on experience with Large Language Models (LLMs).
• Experience with GPT, Gemini, Claude, Llama, Mistral, or similar models.
• Strong understanding of Transformers architecture and Attention Mechanisms.
• Experience with LLM Fine-Tuning, Model Optimization, and Inference.
• Hands-on experience with Hugging Face Transformers and related libraries.
• Knowledge of LoRA, QLoRA, PEFT, and Quantization techniques.
• Solid understanding of Prompt Engineering and Context Management.
• Experience with RAG, embeddings, vector databases, and semantic search.
• Experience developing and deploying production-grade AI applications.
• Knowledge of REST APIs, FastAPI, and cloud-based deployment.

📌 LLM Engineer (Noida)
🏢 Aventra.AI
📍 Noida