Senior Search Engineer

Position Overview

We are looking for a Senior Search Engineer to join our dynamic team in Hyderabad, India. This role involves designing and implementing advanced hybrid search solutions that combine classical information retrieval (IR) techniques with cutting-edge AI technologies, particularly for complex domains such as legal and technical documentation.

Key Responsibilities

• Create hybrid search intelligence systems integrating traditional IR with AI-driven vector search technologies such as FAISS, Pinecone, Weaviate, or Chroma.
• Develop retrieval-augmented generation (RAG) pipelines tailored for specialized domains including patents, legal documents, invoices, and technical literature.
• Fine-tune and evaluate various embeddings, data chunking methods, and context optimization strategies to ensure high recall and relevance in search results.
• Design, optimize, and maintain scalable search pipelines using Solr or Elasticsearch to manage multi-domain corpora effectively.
• Implement relevance tuning techniques including ranking algorithms, synonyms handling, boosting, and custom analyzers specific to domain needs.
• Oversee indexing workflows involving large delta updates, complete reindexing, and caching strategies to maintain performance.
• Build unified APIs enabling efficient search, filtering, and analytics across both structured and unstructured datasets.
• Profile, benchmark, and enhance query latency, recall, and precision to ensure system excellence.
• Collaborate closely with AI engineers to integrate search functionalities with downstream natural language processing (NLP) and RAG pipelines.
• Ensure operational stability and observability of Solr/Elastic search clusters in production environments.

Candidate Requirements

• Minimum of 5 years of hands-on experience developing and scaling search systems based on Solr or Elasticsearch.
• Proven expertise with vector search databases including FAISS, Pinecone, Weaviate, or similar technologies.
• In-depth knowledge of semantic search methodologies, retrieval-augmented generation, and hybrid retrieval systems.
• Experience architecting indexing pipelines for large, frequently updated datasets.
• Strong programming skills in Python, accompanied by experience with deep learning frameworks like PyTorch or TensorFlow.
• Familiarity with LLM orchestration frameworks such as LangChain or LlamaIndex.
• Knowledge of data storage and caching solutions like Redis, PostgreSQL, and MongoDB.
• Excellent debugging capabilities and performance tuning expertise.
• Ability to work autonomously with end-to-end ownership in a fast-paced startup environment.
• Experience implementing machine learning operations (MLOps) practices covering model versioning, deployment, and monitoring.
• Prior exposure or knowledge related to the intellectual property (IP) and LegalTech sectors.
• Background in innovative AI product companies or research and development focused teams.