Job Summary
We are looking for a skilled AI/ML Engineer to design, build, and deploy scalable machine learning solutions with a strong focus on Large Language Models (LLMs). The role involves working on data ingestion, vector databases, model integration, and optimization of AI-driven applications such as RAG systems, semantic search, and intelligent automation.
Roles & Responsibilities- Design, develop, and deploy AI/ML solutions using classical ML and LLM-based architectures.
- Build and maintain end-to-end data pipelines including data scraping, preprocessing, chunking, embedding generation, and storage.
- Implement and optimize vector databases (e.g., VectorDB, Pinecone, FAISS, Weaviate) for semantic search and retrieval.
- Develop RAG (Retrieval-Augmented Generation) pipelines integrating LLMs with structured and unstructured data sources.
- Monitor model performance, latency, and retrieval accuracy; fine-tune models and embeddings as required.
- Collaborate with product, data, and engineering teams to translate business requirements into AI solutions.
- Ensure best practices in model versioning, experimentation, and MLOps.
Required Skills & Qualifications- Strong proficiency in Python and ML frameworks (PyTorch, TensorFlow, scikit-learn).
- Should have 3+ years of experience in similar role.
- Hands-on experience with LLMs (OpenAI, Hugging Face, LLaMA, Mistral, etc.).
- Experience working with vector databases and embedding models.
- Solid understanding of NLP, transformers, embeddings, and similarity search algorithms.
- Experience building production-grade ML systems and APIs (FastAPI, Flask).
- Familiarity with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes).
