People First: At Cognaize, we promote and celebrate a culture of meritocracy driven by empowering people to always aspire to do their best and support each other in individual and team achievement. Meeting and exceeding our customers' expectations is the paramount value for Cognaize. 

We believe that achieving this level of excellence for our customers requires the best and constantly growing team members. As such, we are dedicated to creating an inclusive and nurturing work environment that fosters excellence, collaboration, flexibility, and transparency. We encourage our team members to take ownership of their work, be accountable for their actions, and consistently deliver high-quality results to our customers and each other.

Job Summary:

We are seeking a highly skilled LLM Engineer to join our team. The ideal candidate will have a strong background in developing, fine-tuning, and deploying LLMs using frameworks such as LangChain, LlamaIndex, and Langgraph. You will work with Retrieval-Augmented Generation (RAG) technologies, including FAISS and Pinecone, to optimize performance and enhance retrieval systems. This role requires hands-on experience in LLM fine-tuning and pipeline development to build scalable and efficient AI solutions.

What you'll do:

• Design, build, and optimize LLM pipelines for various applications, ensuring high performance and scalability.
• Implement and integrate frameworks such as LangChain, LlamaIndex, and Langgraph to streamline LLM development.
• Utilize RAG technologies (FAISS, Pinecone) to enhance knowledge retrieval capabilities and improve model efficiency.
• Fine-tune LLMs to adapt them to specific use cases, enhancing performance and accuracy.
• Collaborate with cross-functional teams to design, test, and deploy AI models.
• Conduct research to stay updated with the latest advancements in LLMs and related technologies.
• Troubleshoot and optimize existing LLM solutions to enhance robustness and performance.
• Develop and maintain documentation for LLM workflows and pipelines.
  

What you'll bring:

• Proven experience in working with Large Language Models (LLMs) and developing LLM pipelines.
• Proficiency in frameworks such as LangChain, LlamaIndex, and Langgraph.
• Familiarity with RAG technologies (FAISS, Pinecone) and their application in enhancing LLM performance.
• Strong knowledge of LLM fine-tuning techniques and best practices.
• Experience with programming languages such as Python and frameworks like PyTorch or TensorFlow.
• Ability to work in a collaborative environment with strong communication skills.
• Familiarity with cloud platforms (AWS, Azure, GCP) for deploying and scaling models is a plus.

Cognaize was founded on the belief that the financial industry needed a better way to extract valuable insights from massive amounts of unstructured data. We understood the potential of deep learning and AI to make this process exponentially faster and easier. Using our unparalleled experience in solving complex problems, we built a document automation solution specifically for the financial industry. Now, our clients can transform unstructured data into an ever-better asset that drives more informed decisions and delivers powerful competitive advantages.

We passionately believe that our solution should serve financial specialists, not the other way around. That's why Cognaize was developed for financial experts, by financial experts. Our technology, the Cognaize AI platform, unshackles firms from stacks of forms and documents. Not only are their businesses more efficient and productive, but their staff experiences greater professional fulfillment.

Apply now