Senior Search Engineer

IP Author Inc; Hyderabad; On-site; INR 3,500,000 - 7,000,000; Full time

Job summary

IP Author Inc is building a Generative AI platform for Patent Drafting and IP automation. We are seeking a Senior Search Engineer to design hybrid search systems combining Solr/Elasticsearch with vector search to power retrieval and RAG workflows.

You will own indexing pipelines, embeddings optimization, and latency tuning while collaborating with AI engineers to deliver scalable search across patents, legal docs, invoices, and tech literature.

Qualifications

• 5+ years of experience building and scaling Solr or Elasticsearch-based search systems.
• Proven expertise in Solr/Elasticsearch and vector databases (FAISS, Pinecone, Weaviate, etc.).
• Deep understanding of semantic search, RAG, and hybrid retrieval methods.
• Experience designing indexing pipelines for large and frequently updated corpora.
• Strong Python skills with PyTorch or TensorFlow.
• Familiar with LangChain, LlamaIndex, or equivalent LLM orchestration frameworks.
• Familiarity with Redis, PostgreSQL, and MongoDB
• Deep debugging ability and performance tuning skills.
• Comfortable working independently, owning end-to-end delivery in a startup setup.

Responsibilities

• Design and build hybrid search intelligence that fuses classical IR with modern AI.
• Build hybrid search and retrieval systems combining Solr/Elastic with vector search (FAISS, Pinecone, Weaviate, or Chroma) and optimize latency.
• Develop Retrieval-Augmented Generation (RAG) pipelines for complex legal and technical domains.
• Fine-tune embeddings, chunking strategies, and context optimization for high recall and relevance.
• Design and optimize scalable search pipelines using Solr or Elasticsearch for multi-domain corpora.
• Implement relevance tuning, ranking models, synonyms, boosting, and custom analyzers for domain-specific search.
• Manage indexing workflows (large delta updates, reindexing, cache strategies).
• Build unified APIs for search, filtering, and analytics across structured and unstructured data.
• Profile, benchmark, and improve query latency, recall, and precision.
• Collaborate with AI engineers to integrate search with downstream NLP and RAG pipelines.
• Handle operational reliability and observability for Solr/Elastic clusters in production.

Skills

Solr/Elasticsearch

Vector databases

Semantic search

Python

LangChain/LlamaIndex

LLM orchestration

Redis

PostgreSQL

MongoDB

Performance tuning

Tools

Solr

Elasticsearch

FAISS

Pinecone

Weaviate

Chroma

PyTorch

TensorFlow

LangChain

LlamaIndex

Redis

PostgreSQL

MongoDB

Job description

IP Author is an early-stage, seed-funded startup building a Generative AI platform for Patent Drafting and Intellectual Property automation — transforming how innovation turns into IP assets.

Our mission is to create an end-to-end AI platform that streamlines complex intellectual and legal workflows, enabling teams to innovate faster and operate smarter with trusted automation.

If you love solving retrieval, ranking, and contextual understanding challenges at scale — this is your playground.

What You’ll Do

As a Senior Search Engineer, you’ll design and build hybrid search intelligence that fuses classical IR with modern AI.

• Build hybrid search and retrieval systems combining Solr/Elastic with vector search (FAISS, Pinecone, Weaviate, or Chroma)
• Develop Retrieval-Augmented Generation (RAG) pipelines for complex legal and technical domains.
• Fine-tune and evaluate embeddings, chunking strategies, and context optimization for high recall and relevance.
• Design and optimize scalable search pipelines using Solr or Elasticsearch for multi-domain corpora (patents, legal docs, invoices, and technical literature).
• Implement relevance tuning, ranking models, synonyms, boosting, and custom analyzers for domain-specific search.
• Manage indexing workflows (large delta updates, reindexing, and cache strategies).
• Build unified APIs for search, filtering, and analytics across structured and unstructured data.
• Profile, benchmark, and improve query latency, recall, and precision.
• Collaborate with AI engineers to integrate search with downstream NLP and RAG pipelines.
• Handle operational reliability and observability for Solr/Elastic clusters in production.

What We’re Looking For

• 5+ years of experience building and scaling Solr or Elasticsearch-based search systems.
• Proven expertise in Solr/Elasticsearch and vector databases (FAISS, Pinecone, Weaviate, etc.).
• Deep understanding of semantic search, RAG, and hybrid retrieval methods.
• Experience designing indexing pipelines for large and frequently updated corpora.
• Strong Python skills with PyTorch or TensorFlow.
• Familiar with LangChain, LlamaIndex, or equivalent LLM orchestration frameworks.
• Familiarity with Redis, PostgreSQL, and MongoDB
• Deep debugging ability and performance tuning skills.
• Comfortable working independently, owning end-to-end delivery in a startup setup.

Nice to Have

• Experience implementing MLOps practices for versioning, deployment, and monitoring.
• Knowledge or prior exposure to IP / LegalTech domains.
• Background in deep-tech, AI-first product companies or R&D-driven teams.

Why Join Us

• Join a funded, high-growth AI startup defining the future of IP and LegalTech.
• High-impact role where your code directly shapes product experience and value for global customers.
• Build the core search intelligence powering a next-gen GenAI platform.
• Work directly with leadership to shape search architecture and strategy.
• Competitive pay with potential ESOP for value creators.

Manage Consent

Functional Functional Always active The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network. Preferences Preferences The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user. Statistics Statistics The technical storage or access that is used exclusively for statistical purposes. The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you. Marketing Marketing The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes.