Senior LLM Engineer

About the Role

We are looking for a highly skilled Senior LLM engineer to lead the development of
cutting-edge GenAI applications.
Responsibilities:

• Develop and deploy Advanced Gen-AI applications aligned to the business use cases
• Design, refine, and optimize prompts for multi-modal models to achieve desired outcomes
• Testing the created GenAI solutions and implementing guardrails to prevent unintended/ harmful content.
• Architect and develop conversational AI systems or Retrieval-Augmented Generation (RAG) systems to enhance user interaction.
• Collaborate with team members and explain the findings to the stakeholders

Requirements:

• B.E.\B. Tech\B.S.\Phd Candidates' entries with significant prior experience in the aforementioned fields will be considered.
• 3+ years of experience developing and working on LLM applications.
• Expertise in prompt engineering techniques, including but not limited to chain of thoughts, tree of thoughts, guardrails, and zero-shot or few-shot prompting.
• Knowledge of open-source and proprietary LLMs, such as GPT, Claude, LLaMA, and Mistral.
• Proficiency in Python programming language, with experience in libraries such as numpy and Pandas.
• Hands-on experience working with Langchain, LlamaIndex, Huggingface, or similar frameworks.
• Familiarity with RAG and hands-on experience with self-hosted/cloud-based vector databases.
• A proven ability to work in a cross-discipline environment in defined time frames.
• Experience working with cloud-based systems such as Google Cloud Platform (GCP) or Amazon Web Services (AWS) is highly desirable.
• Strong analytical, problem-solving, and communication skills.

Location: Ahmedabad/ Pune