Search Engineer

Required Skills & Experience

•6+ years of professional backend or full-stack engineering experience with a deep Python focus (async patterns, type annotations, testing, and production-grade service design.) •Proven experience designing and deploying cloud-native applications (GCP strongly preferred; AWS or Azure considered). •Hands-on experience building resilient microservices and RESTful/gRPC APIs. •Strong understanding of containerization (Docker), orchestration (Kubernetes), and serverless paradigms. •Strong grounding in SOLID design principles and software craftsmanship. •Good communicator who thrives in cross-functional, agile teams alongside ML engineers, architects, and product owners. •Comfortable using AI tools to accelerate development throughput. •Large enterprise experience

Nice to Have Skills & Experience

•Experience with search platforms such as Elasticsearch, OpenSearch, Solr, or Algolia - index management, query DSL, relevance tuning. •Familiarity with vector search concepts and tooling such as embeddings, approximate nearest neighbor (ANN), FAISS, Pinecone, Weaviate, or similar. •Exposure to ML/AI patterns: RAG pipelines, LLM integration, prompt engineering, or fine-tuning workflows. •Experience with AI orchestration frameworks such as LangChain, LangGraph, or Google ADK. •Infrastructure-as-code experience (Terraform, Pulumi) and mature CI/CD pipeline ownership.

Job Description

-Build and own production search & AI services end-to-end (Python APIs, ML inference pipelines [embeddings, transformers, LLMs], and real-time, event-driven systems on GCP) -Contribute to modern search infrastructure, implementing hybrid retrieval (keyword + vector + reranking), Elasticsearch pipelines, vector databases, and relevance measurement through experimentation and metrics. -Set a high engineering bar, leading design discussions, enforcing CI/CD and observability best practices, and actively mentoring through reviews and knowledge sharing