Responsibilities
- Build and enhance search and retrieval systems using advanced NLP and information retrieval techniques.
- Process and analyze multi-format documents (text, tables, images) to extract and structure key insights.
- Design and implement entity extraction , relationship modeling , and text classification pipelines.
- Develop efficient indexing and embedding strategies to power high-performance semantic search.
- Conduct experiments to evaluate, fine-tune, and improve model accuracy and robustness.
- Develop and maintain domain-specific language models for specialized use cases.
- MS/PhD in Computer Science, NLP, Information Retrieval, or related field .
- 2+ years of hands-on experience building production-grade NLP or ML systems .
- Strong proficiency in Python , ML frameworks, and libraries such as spaCy , Hugging Face , or NLTK .
- Experience with search technologies (e.g., Elasticsearch, graph databases, vector databases).
- Hands-on experience designing and deploying RAG (Retrieval-Augmented Generation) pipelines , including document retrieval, embedding stores, and LLM integration.
- Familiarity with LLM-based applications and modern AI toolchains.
Preferred qualifications
- Experience training or fine-tuning proprietary algorithms.
- Exposure to agentic AI systems or multi-step reasoning frameworks.
- Interest in applying AI to real-world operational challenges.
About the company
We’re a fast-growing AI company transforming one of the world’s largest and most operationally complex industries through intelligent automation. The organization is backed by leading investors and is scaling rapidly, with a team of engineers, data scientists, and domain experts focused on embedding AI directly into real-world workflows.
Our mission is to digitize and automate field operations by building production-ready AI agents that handle document understanding, question answering, and decision support at scale. The team blends deep technical expertise with hands-on industry experience, and we’re now expanding our applied AI capabilities during a critical phase of growth.
Tags & focus areas
Used for matching and alerts on DevFound Fulltime Remote Ai Machine Learning Data Science Nlp Generative Ai