Posted on: 15/07/2025
Job Summary :
Key Responsibilities :
- Design and develop NLP models for tasks such as text classification, summarization, information extraction, semantic search, etc.
- Build and deploy advanced deep learning architectures (Transformer-based models, BERT, GPT, etc.).
- Leverage LangChain to build intelligent LLM-powered applications and pipelines.
- Work with RAG pipelines to combine LLMs with external data sources.
- Create and optimize prompt templates and manage interactions with models like GPT-4, Claude, or open-source LLMs.
- Collaborate with data engineering and product teams to deploy models at scale.
- Perform model evaluation, fine-tuning, and experimentation for performance optimization.
- Document methodologies and contribute to internal best practices around prompt engineering and LLM usage.
Required Skills :
- Strong proficiency in Python and ML libraries such as scikit-learn, TensorFlow, PyTorch, Hugging Face Transformers.
- Deep understanding of NLP techniques, including tokenization, embeddings, text generation, named entity recognition, etc.
- Hands-on experience with LLMs and building applications using LangChain or similar frameworks.
- Strong experience on public cloud (GCP / AWS / Azure)
- Familiarity with vector databases (Pinecone, FAISS, Weaviate, etc.).
- Knowledge of MLOps practices and model deployment tools (Docker, MLFlow, FastAPI, etc.).
- Experience working with cloud platforms (AWS, GCP, or Azure).
- Strong analytical, problem-solving, and communication skills.
Nice to Have :
- Familiarity with knowledge graphs, semantic search, or question answering systems.
- Contributions to open-source or publications in the AI/ML/NLP domain.
Education :
Please Note : The interview will be F2F in Pune, so please confirm your availability for the same as well.
Did you find something suspicious?