NLP Engineering Intern

NLP Engineering Intern at Blank Slate NLP Engineering Intern at Blank Slate in Fairview, New Jersey Posted in about 16 hours ago.

Type:

intern

Job Description:

Blank Slate is building the next generation of systems to help teams move faster, think better, and operate at scale. We create intuitive, high-impact products, leveraging data science, cognitive science, and a strong user interface, that solve real problems for modern organizations. Our team values ownership, curiosity, and speed - bringing together engineers and builders who are excited to tackle complex challenges and turn ideas into reality. Opportunity We are looking for a specialized NLP Engineer to join our Data Science team. In this role, you will be the resident expert on all things Natural Language Processing (NLP) and Large Language Models (LLMs). You will work directly alongside our Data Scientists, taking ownership of the unstructured text data lifecycle. Your primary mission will be to design, build, and optimize text preprocessing pipelines, extracting clean, structured, and meaningful features from raw text to feed into our core predictive models. If you love wrestling with messy text data and know your way around Hugging Face and modern LLMs, we want you on our team.

Key Responsibilities Text Preprocessing & Pipeline Building:

Design and implement robust data pipelines to clean, normalize, and preprocess large volumes of unstructured textual data.

Feature Engineering:

Extract meaningful signals from text using traditional NLP techniques (tokenization, lemmatization, NER, POS tagging) and modern embedding models.

LLM Integration:

open-source Large Language Models (e.g., LLaMA, BERT) for text classification, summarization, entity extraction, and data augmentation.

Collaboration:

Partner closely with our core Data Scientists and Product Managers to understand their modeling needs, ensuring the text data you process is perfectly formatted for downstream machine learning models.

Optimization:

Evaluate and improve the efficiency of text processing scripts, ensuring they can scale with growing datasets.

Required Qualifications Experience:

1+ years of experience in Data Engineering, Machine Learning, or Data Science with a heavy emphasis on NLP. Both academic (course project, research project) and industry (fulltime, intern, contractor) experience count.

Programming:

Strong proficiency in Python and familiar with data manipulation libraries (Pandas, NumPy).

NLP/LLM Tooling:

Hands-on experience with NLP libraries and frameworks such as Hugging Face, transformers, vLLM, PyTorch.

Vector databases:

Pinecone, Milvus, Weaviate, pgvector. Nice to Have Understand basic statistics (e.g., confidence interval, hypothesis testing) and machine learning theory foundation (e.g., gradient boosting, regularization, bias-variance tradeoff). Experience with GCP and Docker. What We Offer Competitive salary from $40 to $60 per hour. Compensation is hourly for the summer internship role

High-Impact Work:

Your pipelines won't sit on a shelf. The features and clean data you generate will directly feed our core machine learning models and drive critical business decisions from day one. You will see the immediate results of your efforts as they solve complex, real-world problems.

Technical Ownership:

You will be our resident NLP expert. You'll have the autonomy to choose the right tools for the job, shape our AI architecture, and build systems from the ground up. How to

Apply :

Please submit your resume, 50 words or less why this opening fits you, and a link to your GitHub repo showcasing any relevant NLP or text-processing work you have built.