Job SummaryThe Search Engineer / Tech Lead will lead the design, development, optimization, and operation of the enterprise search layer for Client. This role is responsible for delivering secure, grounded, scalable, and supportable search experiences using Lucidworks Fusion or a comparable enterprise search platform.
The position will initially focus on single-turn answer experiences and evolve toward multi-turn conversational search. The Search Engineer / Tech Lead will combine hands-on engineering with technical leadership to translate customer journeys and business requirements into scalable search, retrieval, and AI solutions across web, content, commerce, and enterprise platforms.
Key ResponsibilitiesSearch Platform & Retrieval Engineering- Design and implement collections, schemas, connectors, index and query pipelines, query profiles, and REST API integrations using Lucidworks Fusion or comparable enterprise search technologies.
- Build and optimize lexical, semantic, vector, and neural hybrid retrieval solutions.
- Tune embeddings, blend weights, thresholds, boosting, filtering, facets, synonyms, and fallback behaviors to improve search relevance.
- Leverage behavioral signals and usage data to improve relevance, recommendations, personalization, and successful search outcomes.
- Establish relevance benchmarks, automated regression tests, citation and grounding tests, latency targets, and per-query cost measures.
- Troubleshoot ingestion, indexing, Solr, Kubernetes/AWS, APIs, search pipelines, model endpoints, and front-end integrations.
Conversational Search & Generative AI- Engineer single-turn and multi-turn conversational search experiences incorporating intent recognition, entity extraction, query rewriting, clarification, and session context.
- Implement grounded Retrieval-Augmented Generation (RAG) solutions that retrieve approved sources, provide supporting citations, and apply appropriate fallback behavior when confidence or evidence is insufficient.
- Integrate search solutions with enterprise LLM services and AI gateways using prompt controls, model configuration, rate limits, error handling, latency management, and cost governance.
- Optimize search experiences for product numbers, specifications, availability, certificates, manuals, application notes, and related support content.
- Implement appropriate guardrails for transactional and product/SKU queries, low-confidence results, insufficient grounding, and zero-result scenarios.
Integration, Delivery & Operations- Partner with AEM and front-end engineering teams to deliver accessible search results, conversational answers, follow-up suggestions, and facets aligned with established design standards.
- Manage search-platform configuration as code using GitLab, peer reviews, automated testing, and CI/CD practices.
- Instrument and monitor key search metrics, including click-through rates, zero-result searches, no-click activity, reformulations, abandonment, task completion, latency, and pipeline health.
- Develop architecture diagrams, deployment documentation, runbooks, configuration standards, and knowledge-transfer materials.
- Collaborate with security, privacy, legal, architecture, product, content, and business teams on access controls, data handling, AI guardrails, and release readiness.
- Participate in AI development lifecycle and Agile delivery activities.
- Translate customer journeys and business requirements into technical designs, backlog items, acceptance criteria, and measurable outcomes.
- Provide technical leadership while supporting production readiness, troubleshooting, and continuous search optimization.
- Required Qualifications
- Bachelor's degree in Computer Science, Information Systems, Engineering, Data Science, or a related discipline, or equivalent practical experience.
- 5+ years of experience in search engineering, information retrieval, or enterprise application development.
- Substantial experience with Lucidworks Fusion or comparable enterprise search technologies such as Solr/Lucene, Elasticsearch/OpenSearch, Algolia, Vespa, or Azure AI Search.
- Hands-on expertise with schemas, analyzers, tokenization, synonyms, faceting, boosting, filtering, relevance scoring, query debugging, connectors, signals, custom pipeline stages, and REST APIs.
- Practical experience with semantic search, embeddings, approximate nearest-neighbor retrieval, neural hybrid ranking, and relevance evaluation.
- Experience implementing RAG, grounding, prompt design, citations, guardrails, and fallback patterns.
- Experience with multi-turn conversational context, session design, intent classification, and entity extraction.
- Experience deploying or operating search workloads in AWS and Kubernetes, including observability and production troubleshooting.
- Proficiency in Java and/or Python, JSON, HTTP APIs, Git, automated testing, and CI/CD practices.
- Ability to translate business requirements and customer journeys into scalable technical designs and measurable outcomes.
- Strong written and verbal communication skills with the ability to collaborate with both technical and nontechnical stakeholders.
- Ability to work independently, prioritize competing initiatives, resolve ambiguity, and effectively transfer technical knowledge.
Preferred Qualifications- Experience implementing, upgrading, or administering Lucidworks Fusion 5.x in a self-hosted environment.
- Experience with Fusion AI, RAY, Learning-to-Rank, Relevance Workbench, Analytics Studio, Commerce Studio, A/B testing, or comparable technologies.
- Integration experience with AEM as a Cloud Service, commerce platforms, product catalogs, digital assets, or certificate/document services.
- Knowledge of Redis or similar session-store technologies.
- Experience with multilingual search, part-number/SKU handling, permissions-aware retrieval, and blending structured and unstructured content.
- Experience working in compliance-sensitive or document-intensive environments.
- Familiarity with accessibility standards, privacy practices, secure AI development, responsible AI, and production monitoring.
Certifications- Relevant search, cloud, or AI certifications are preferred.
- Key Deliverables & Outcomes
- Production-ready architecture supporting lexical, semantic, hybrid, and conversational search.
- Grounded conversational search pipelines capable of retaining context, recognizing intent and entities, citing supporting evidence, and applying appropriate fallback behavior.
- Relevance benchmarks and regression testing for priority customer journeys and product-search patterns.
- Operational dashboards and alerts covering search quality, adoption, latency, failures, and model or gateway dependencies.
- Comprehensive runbooks, deployment documentation, configuration standards, and knowledge-transfer materials.
