Design and implement RAG pipelines to enhance information retrieval and generation tasks.
Develop a deep understanding of the differences between prompting and training LLMs and apply this knowledge to optimize model performance.
Test and evaluate various LLMs (e.g., OpenAI, Llama, Claude) to identify the best fit for specific use cases.
Analyze and address issues related to model speed, performance, and cost-effectiveness.
Collaborate with cross-functional teams to integrate AI solutions into production environments.
Stay up-to-date with the latest advancements in AI and machine learning to improve our solutions continuously.
Requirements & Skills:
9+ years of professional hands-on development experience using Python, especially machine learning frameworks and libraries (e.g., TensorFlow, PyTorch).
Proven experience in setting up and optimizing RAG pipelines.
Strong understanding of prompting vs. training for large language models.
Hands-on experience with testing and comparing different LLMs (OpenAI, Llama, Claude, etc.).
Familiarity with the challenges of model speed and cost optimization.
Proficiency
Excellent problem-solving skills and attention to detail.
