👋 About Mentium

Mentium is an AI Copilot for FinOps in logistics

We ingest emails and capture, structure, and centralize payment-related documents, automating data entry into TMSs and ERPs while ensuring continuous AI-powered audits of all accounts payable and accounts receivable transactions in logistics.

⭐ About You

We are excited to bring on board a Founding Machine Learning Engineer to join our dynamic team. You will lead the development and enhancement of our finetuned LLMs models and retrieval-augmented generation (RAG) capabilities, tackling novel problems and crafting innovative solutions. You understand how to conceptualize and deploy MVPs rapidly.

Responsibilities

• Finetune LLMs/ Train NLP models to address key business challenges.
• Lead the development of top-tier retrieval models optimized for the RAG process, ensuring the delivery of highly relevant source material for generative models.
• Enhance our RAG & Knowlege Graph framework to improve document encoding, scoring, and selection mechanisms, focusing on sophisticated natural language understanding.
• Undertake rigorous experimentation and analysis to benchmark retrieval models against industry standards, focusing on both precision and adaptability for generative tasks.
• Collaborate with product and engineering teams to integrate NLP features and retrieval components into our products.
• Develop frameworks for processing and understanding large volumes of documents.
• Drive innovation by staying abreast of emerging trends and methodologies in retrieval systems and their applications within RAG frameworks.
• Create pipelines to process and analyze documents on a large scale to provide insights for customers.
  
  

Who You Are

• Experience: You bring 5+ years of experience in backend engineering, particularly in environments where NLP and retrieval models are developed and deployed.
• Technical Skills: Proficient in Python and familiar with NLP libraries such as NLTK, spaCy, or Hugging Face Transformers. Demonstrated experience with modern retrieval techniques such as dense passage retrieval (DPR), contrastive learning, and other advanced retrieval methods.
• Database and Data Handling: Strong understanding of SQL databases and efficient data handling techniques relevant to NLP tasks.
• Systems Thinking: Ability to develop and scale NLP and retrieval solutions, recognizing patterns that help in automating and improving text processing tasks.
• Adaptability: Thrive in a fast-paced and high-autonomy environment, capable of making informed decisions quickly that influence the strategic direction of our NLP initiatives.
  
  

Preferred Qualifications

• A Master or PHD degree in Computer Science, Linguistics, or a related field with a strong focus on NLP.
• Experience with transformer models and sequence-to-sequence learning, particularly as it relates to document retrieval for generation.
• Experience with distributed systems
• Previous work in a role where NLP models directly impacted business outcomes, such as in customer service automation, content recommendation, or risk management.
  
  

We'll Provide

• New laptop/equipment of your choice.
• Top of the line health, dental, and vision insurance.
• Unlimited PTO.
• (Optional) Relocation to Austin.