Senior NLP Engineer

SiftHub is a revenue acceleration AI platform that unlocks 10x productivity for sales and solutions teams. It serves as a central hub to collate and sift through all your conversations, knowledge and deal context scattered across Drive, Sharepoint, Confluence, Gong, CRM, Slack, Zendesk.

From last-minute meeting prep to competitive intel and RFPs to buyer Q&A, our autonomous agents unblock deals so your SEs and AEs can focus on engaging with customers.

As a member of our team, you'll be at the forefront of this exciting technology revolution, working alongside some of the brightest minds in the industry to bring our platform to life. We're looking for individuals who are passionate about AI and its potential to drive real-world impact.

Whether you're an AI expert or an aspiring one, SiftHub offers an environment that supports and challenges you, enabling your growth and success. Join us today and help us shape the future of AI for enterprises!

Responsibilities :

Design and develop engaging, effective, and unambiguous NLP systems, taking into account user intent, context, and desired results

Collaborate with cross-functional teams, including product managers, UI / UX designers, and developers, to develop the best user experiences

Conduct user research and evaluate user feedback in order to continuously finetune the models

Stay updated on industry trends, new technologies, and best practices in AI, NLP, and conversational design

Develop and keep up-to-date engineering documentation, including guidelines, best practices, and utilization examples

Contribute to the process of quality assurance and devops by identifying and resolving issues to ensure model effectiveness and user satisfaction

Actively participate in code reviews, architecture discussions, and technical debates to ensure quality

Mentor developers by providing guidance, feedback, and support throughout their career growth

Requirements :

Bachelor’s or Master’s degree in Computer Science, Information Technology with a focus on language processing

6+ years of experience in developing NLP-based applications, with strong proficiency in Python

Experience in machine learning frameworks, libraries and large language models (LLMs) like BERT, GPT, or other transformer-based architectures, and practical knowledge of retrieval-augmented generation (RAG) systems.

Expertise in designing, implementing, and exposing RESTful APIs or microservices using FastAPI, ensuring scalable, high-performance interfaces for NLP applications.

In-depth understanding of various NLP techniques for text processing, semantic extraction, tokenization, named entity recognition, dependency parsing, and knowledge of embeddings (e.g., Word2Vec, GloVe, transformers).

Strong grasp of data structures and modeling techniques, with the ability to apply these skills to enhance language models and NLP pipelines.

Experience with relevant machine learning frameworks and libraries, such as TensorFlow, PyTorch, Hugging Face's Transformers, or SpaCy, for developing and fine-tuning models.

Experience in implementing the products lifecycle - design, development, quality, deployment, maintenance

Excellent communication and decision making skills