Experience: 1 - 3 YearsOpenings: 2Package: as per industry standards
Job Summary:
Key Responsibilities:
- Design and develop NLP models for Intent Classification and Entity Recognition.
- Prepare, clean, and label conversational datasets.
- Train, fine-tune, and evaluate machine learning models for conversational AI.
- Build hybrid AI systems using ML-based intent detection with LLM fallback.
- Develop conversation routing logic based on confidence scores.
- Optimize model accuracy, latency, and inference performance.
- Integrate ML models with Python backend services and REST APIs.
- Design conversation flows for AI Voice Bots and Chatbots.
- Work with Prompt Engineering for LLM fallback responses.
- Build and maintain RAG (Retrieval-Augmented Generation) pipelines.
- Monitor model performance and retrain models when required.
- Collaborate with Backend, Frontend, and Product teams.
Required Skills:
- Strong Python programming
- Machine Learning
- Natural Language Processing (NLP)
- Intent Classification
- Text Classification
- Named Entity Recognition (NER)
- scikit-learn
- PyTorch or TensorFlow
- Hugging Face Transformers
- Sentence Transformers
- Model Training & Fine-Tuning
- Model Evaluation (Precision, Recall, F1-Score)
- REST APIs
- Git
- Prompt Engineering
- RAG
- Vector Databases (Qdrant, Pinecone, Weaviate, Chroma)
- LangChain / LangGraph / LlamaIndex
Valuable to Have:
- Experience building AI Voice Bots
- Hybrid ML + LLM architectures
- Conversation Flow Design
- Speech-to-Text (STT) and Text-to-Speech (TTS) integrations
- Production deployment of ML models