Natural Language Processing Engineer

Oasys Tech Solutions; Khordha; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Oasys Tech Solutions in Odisha, India is seeking an NLP Engineer with 4+ years of experience to design, develop, and deploy NLP and ML solutions for real-world applications.

The role focuses on text classification, NER, sentiment analysis, and semantic search, with experience in Transformer models and RAG pipelines. You will work with Python, PyTorch/TensorFlow, Hugging Face, and FastAPI to build scalable AI services.

Qualifications

• 4+ years of relevant experience in NLP/AI/ML.
• Strong Python programming skills.
• Hands-on experience with PyTorch or TensorFlow.
• Experience with Transformers and models like BERT, RoBERTa, T5.
• Hands-on experience with Hugging Face.
• Experience with LLMs / Generative AI.
• Knowledge of RAG, embeddings and vector databases.
• Experience with LangChain or similar frameworks.
• Exposure to cloud platforms.

Responsibilities

• Develop and deploy NLP and ML solutions for real-world applications.
• Work on text classification, NER, sentiment analysis, information extraction and semantic search.
• Develop and fine-tune Transformer-based models such as BERT, RoBERTa, T5, etc.
• Build applications using LLMs and Generative AI.
• Design and implement RAG pipelines.
• Work with embeddings, vector databases and semantic search.
• Perform model fine-tuning using LoRA/PEFT and other optimization techniques.
• Develop and deploy NLP/AI models using Python, PyTorch/TensorFlow and Hugging Face.
• Evaluate and optimize models for accuracy, latency, scalability and reliability.
• Build APIs using FastAPI/REST APIs and integrate AI models into applications.
• Work with large and unstructured text datasets.
• Troubleshoot RAG retrieval issues, hallucinations and model performance.
• Collaborate with Data Scientists, ML Engineers and Software Development teams.
• Research and implement the latest developments in NLP, LLMs and Generative AI.

Skills

Python

NLP concepts

4+ years experience

LLMs / Generative AI

Transformer models

Hugging Face

RAG / embeddings

Prompt engineering

LoRA / PEFT

API development

Education

Bachelors/Masters in CS/IT/AI/ML or related

Tools

PyTorch

TensorFlow

Hugging Face

FastAPI

Docker

Git

GCP/AWS/Azure

Vector databases (FAISS/Pinecone/Milvus)

Job description

NLP Engineer

4+ Years Experience

Key Responsibilities:

• Develop and deploy NLP and Machine Learning solutions for real-world applications.
• Work on text classification, NER, sentiment analysis, information extraction and semantic search.
• Develop and fine-tune Transformer-based models such as BERT, RoBERTa, T5, etc.
• Build applications using LLMs and Generative AI.
• Design and implement RAG (Retrieval-Augmented Generation) pipelines.
• Work with embeddings, vector databases and semantic search.
• Perform model fine-tuning using LoRA/PEFT and other optimization techniques.
• Develop and deploy NLP/AI models using Python, PyTorch/TensorFlow and Hugging Face.
• Evaluate and optimize models for accuracy, latency, scalability and reliability.
• Build APIs using FastAPI/REST APIs and integrate AI models into applications.
• Work with large and unstructured text datasets.
• Troubleshoot RAG retrieval issues, hallucinations and model performance.
• Collaborate with Data Scientists, ML Engineers and Software Development teams.
• Research and implement the latest developments in NLP, LLMs and Generative AI.

Required Skills

• 4+ years of relevant experience in NLP / AI / Machine Learning.
• Strong Python programming skills.
• Strong understanding of NLP and Machine Learning concepts.
• Hands-on experience with PyTorch or TensorFlow.
• Experience with Transformers, BERT, RoBERTa, T5 or similar models.
• Hands-on experience with Hugging Face.
• Experience working with LLMs / Generative AI.
• Strong understanding of RAG, embeddings and vector databases.
• Experience with LangChain / LlamaIndex or similar frameworks.
• Knowledge of Prompt Engineering and LLM fine-tuning.
• Experience with LoRA / PEFT is preferred.
• Experience with FastAPI/REST APIs.
• Knowledge of Docker and Git/GitHub.
• Exposure to AWS/Azure/GCP is preferred.
• Experience with FAISS, Pinecone, Milvus, Weaviate or ChromaDB is an advantage.

Education

• Bachelor's/Master's degree in Computer Science, IT, AI/ML, Data Science, Engineering or related field.