Seeking a skilled and hands-on AI/LLM Engineer to join the AI development team.
Ideal candidate will have strong experience with Large Language Models (LLMs), including prompt tuning, model finetuning, and invocation orchestration.
Role focuses on designing, integrating, and optimizing LLM-powered systems to improve the overall user experience.
Will collaborate closely with product and engineering teams to evaluate, refine, and deploy conversational and generative AI solutions in real-time applications.
Key Responsibilities
Perform LLM finetuning using techniques such as prompt tuning and lightweight adaptation methods.
Build and manage invocation pipelines from applications to different LLMs (e.g., OpenAI, Anthropic, Mistral, local models).
Design prompting strategies to elicit accurate, consistent, and contextually relevant model outputs.
Define and evaluate LLM responses based on use case relevance, factual accuracy, and UX quality.
Continuously iterate and improve the response quality and user experience based on feedback and metrics.
Collaborate with product managers and designers to align AI behavior with business needs and product goals.
Required Skills & Experience
Proven experience working with LLMs, including prompt engineering and finetuning techniques (e.g., LoRA, PEFT, adapters).
Familiarity with frameworks such as Hugging Face Transformers, LangChain, or LLamaIndex.
Experience in real-time LLM integration into web or mobile applications.
Strong understanding of response evaluation frameworks, including qualitative and quantitative methods.
Programming proficiency in Python; experience with deployment tools and APIs is a plus.
Ability to work in a fast-paced, collaborative, and iterative development environment.