- Strong proficiency in Python and frameworks like LangChain,ReAct, Hugging Face Transformers.

- Experience with vector databases (Pinecone, Milvus, Weaviate) and search engines (ElasticSearch, FAISS).

- Familiarity with LLMs and prompt engineering.

- Develop end-to-end RAG architectures integrating retrieval systems with generative AI models especially using google services(Google ADK).

- Implement document chunking, embedding generation, and vector indexing for efficient retrieval.

- Preprocess and structure large-scale datasets for semantic search.

- Maintain and update embeddings in vector databases (e.g., Pinecone, Weaviate, FAISS).

- Connect retrieval components with LLMs (e.g., GPT, LLaMA, Falcon) using frameworks like LangChain or LlamaIndex.

- Optimize prompt engineering for contextual accuracy and minimal hallucination.

- Fine-tune retrieval and ranking algorithms for precision and recall, Implement continuous evaluation and retraining strategies.

- Hands-on experience with GCP, Knowledge of containerization (Docker) and orchestration (Kubernetes).

- Strong problem-solving and optimization skills.