Bangalore, Karnataka, India
Information Technology
Full-Time
INDUSKART ENGITECH LLP
Overview
Job Summary:
We are seeking a skilled Python developer with experience in natural language processing (NLP) and machine learning (ML) to build a local document ingestion and Q&A system. The successful candidate will be responsible for designing and implementing a solution that processes a large volume of documents (PDFs, text files, etc.), indexes them for efficient retrieval, and integrates these capabilities into a chatbot-like interface.
Key Responsibilities:
- Develop Python-based tools to read, parse, and index documents (PDFs, Word files, etc.).
- Integrate document indexing solutions (e.g., ElasticSearch, FAISS, or LlamaIndex).
- Implement retrieval-augmented generation (RAG) pipelines by connecting document retrieval results to language models.
- Work with open-source language models (such as GPT4All or Hugging Face Transformers) and integrate them into the application.
- Design and maintain APIs or interfaces to enable users to query documents via a chatbot.
- Optimize the performance of indexing and query-handling processes.
- Ensure the system runs efficiently in a local environment, respecting privacy and security requirements.
- Collaborate with product owners to refine requirements and deliver features on time.
- Document the code, architecture, and workflows for internal use and future development.
Required Skills:
- Strong proficiency in Python and its ecosystem.
- Hands-on experience with NLP libraries and frameworks (e.g., Hugging Face Transformers, spaCy).
- Familiarity with vector search libraries (FAISS, Milvus) or traditional search solutions (ElasticSearch, Apache Solr).
- Understanding of language model integration (GPT-based models, Llama-based models, or other open-source LLMs).
- Experience working with document processing libraries (PyPDF2, PDFminer, textract).
- Knowledge of machine learning concepts and familiarity with pre-trained model fine-tuning.
- Strong problem-solving skills and attention to detail.
- Good communication skills and the ability to work independently or as part of a team.
Preferred Skills:
- Experience with Retrieval-Augmented Generation (RAG) pipelines.
- Familiarity with cloud services and on-premise deployments.
- Exposure to front-end frameworks or API development (e.g., Flask, FastAPI) for building a user interface or endpoint for the chatbot.
- Previous experience in a similar project or building AI-driven applications.
Job Types: Full-time, Permanent
Pay: ₹15,000.00 - ₹30,000.00 per month
Benefits:
- Provident Fund
Location Type:
- In-person
Schedule:
- Day shift
Work Location: In person
Speak with the employer
+91 9726419410
Similar Jobs
View All
Talk to us
Feel free to call, email, or hit us up on our social media accounts.
Email
info@antaltechjobs.in