{"schemaVersion":"jobsearcher.job.v1","id":"8017dcfe3f293aef7670d55d","url":"https://jobsearcher.com/jobs/8017dcfe3f293aef7670d55d","canonicalUrl":"https://jobsearcher.com/jobs/8017dcfe3f293aef7670d55d","title":"Lead AI Engineer","description":"Job Title: Lead AI Engineer\nLocation: Austin, Texas (Hybrid)\n\nDuration: Longterm Contract\n\nLead AI Engineer (Search Modernization)\n\nMandatory Skills: Elastic Search, OpenSearch, Python, LLM, GenAI, Semantic Search, Re-Ranking, AWS, Search Engineer\n\nJob Description:\nWe are looking for an AI Engineer to modernize and enhance our existing regex/keyword-based Elastic Search system by integrating state-of-the-art semantic search, dense retrieval, and LLM-powered ranking techniques.\nThis role will drive the transformation of traditional search into an intelligent, context-aware, personalized, and high-precision search experience.\n\nThe ideal candidate has hands-on experience with Elastic Search internals, information retrieval (IR), embedding-based search, BM25, re-ranking, LLM-based retrieval pipelines, and AWS cloud deployment.\n\nRoles & Responsibilities\n\nModernizing the Search Platform\n\nAnalyze limitations in current regex & keyword-only search implementation on ElasticSearch.\nEnhance search relevance using:\nBM25 tuning\nSynonyms, analyzers, custom tokenizers\nBoosting strategies and scoring optimization\nIntroduce semantic / vector-based search using dense embeddings.\n2. LLM-Driven Search & RAG Integration\n\nImplement LLM-powered search workflows including:\nQuery rewriting and expansion\nEmbedding generation (OpenAI, Cohere, Sentence Transformers, etc.)\nHybrid retrieval (BM25 + vector search)\nRe-ranking using cross-encoders or LLM evaluators\nBuild RAG (Retrieval Augmented Generation) flows using ElasticSearch vectors, OpenSearch, or AWS-native tools.\n3. Search Infrastructure Engineering\n\nBuild and optimize search APIs for latency, relevance, and throughput.\nDesign scalable pipelines for:\nIndexing structured and unstructured text\nMaintaining embedding stores\nReal-time incremental updates\nImplement caching, failover, and search monitoring dashboards.\n4. AWS Cloud Delivery\n\nDeploy and operate solutions on AWS, leveraging:\nOpenSearch Service or EC2-managed ElasticSearch\nLambda, ECS/EKS, API Gateway, SQS/SNS\nSageMaker for embedding generation or re-ranking models\nImplement CI/CD for search models and pipelines.\n5. Evaluation & Continuous Improvement\n\nDevelop search evaluation metrics (nDCG, MRR, precision@k, recall).\nConduct A/B experiments to measure improvements.\nTune ranking functions and hybrid search scoring.\nPartner with product teams to refine search behaviors with real usage patterns.\nRequired Skills & Qualifications\n\n5–10 years of experience in AI/ML, NLP, or IR systems, with hands-on search engineering.\nStrong expertise in ElasticSearch/OpenSearch: analyzers, mappings, scoring, BM25, aggregations, vectors.\nExperience with semantic search:\nEmbeddings (BERT, SBERT, Llama, GPT-based, Cohere)\nVector databases or ES vector fields\nApproximate nearest neighbor (ANN) techniques\nWorking knowledge of LLM-based retrieval and RAG architectures.\nProficient in Python; familiarity with Java/Scala is a plus.\nHands-on AWS experience (OpenSearch, SageMaker, Lambda, ECS/EKS, EC2, S3, IAM).\nExperience building and deploying APIs using FastAPI/Flask and containerizing with Docker.\nFamiliar with typical IR metrics and search evaluation frameworks.\nPreferred Skills\n\nKnowledge of cross-encoder and bi-encoder architectures for re-ranking.\nExperience with query understanding, spell correction, autocorrect, and autocomplete features.\nExposure to LLMOps / MLOps in search use cases.\nUnderstanding of multi-modal search (text + images) is a plus.\nExperience with knowledge graphs or metadata-aware search.","company":"Software Technology","rawCompany":"software technology","city":"Austin","state":"TX","isRemote":false,"isActive":false,"createdAt":"2026-04-14T10:44:02.157Z","occupations":[{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"}],"industries":[{"code":"519290","title":"Web Search Portals and All Other Information Services","slug":"web-search-portals-and-all-other-information-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Lead AI Engineer","description":"Job Title: Lead AI Engineer\nLocation: Austin, Texas (Hybrid)\n\nDuration: Longterm Contract\n\nLead AI Engineer (Search Modernization)\n\nMandatory Skills: Elastic Search, OpenSearch, Python, LLM, GenAI, Semantic Search, Re-Ranking, AWS, Search Engineer\n\nJob Description:\nWe are looking for an AI Engineer to modernize and enhance our existing regex/keyword-based Elastic Search system by integrating state-of-the-art semantic search, dense retrieval, and LLM-powered ranking techniques.\nThis role will drive the transformation of traditional search into an intelligent, context-aware, personalized, and high-precision search experience.\n\nThe ideal candidate has hands-on experience with Elastic Search internals, information retrieval (IR), embedding-based search, BM25, re-ranking, LLM-based retrieval pipelines, and AWS cloud deployment.\n\nRoles & Responsibilities\n\nModernizing the Search Platform\n\nAnalyze limitations in current regex & keyword-only search implementation on ElasticSearch.\nEnhance search relevance using:\nBM25 tuning\nSynonyms, analyzers, custom tokenizers\nBoosting strategies and scoring optimization\nIntroduce semantic / vector-based search using dense embeddings.\n2. LLM-Driven Search & RAG Integration\n\nImplement LLM-powered search workflows including:\nQuery rewriting and expansion\nEmbedding generation (OpenAI, Cohere, Sentence Transformers, etc.)\nHybrid retrieval (BM25 + vector search)\nRe-ranking using cross-encoders or LLM evaluators\nBuild RAG (Retrieval Augmented Generation) flows using ElasticSearch vectors, OpenSearch, or AWS-native tools.\n3. Search Infrastructure Engineering\n\nBuild and optimize search APIs for latency, relevance, and throughput.\nDesign scalable pipelines for:\nIndexing structured and unstructured text\nMaintaining embedding stores\nReal-time incremental updates\nImplement caching, failover, and search monitoring dashboards.\n4. AWS Cloud Delivery\n\nDeploy and operate solutions on AWS, leveraging:\nOpenSearch Service or EC2-managed ElasticSearch\nLambda, ECS/EKS, API Gateway, SQS/SNS\nSageMaker for embedding generation or re-ranking models\nImplement CI/CD for search models and pipelines.\n5. Evaluation & Continuous Improvement\n\nDevelop search evaluation metrics (nDCG, MRR, precision@k, recall).\nConduct A/B experiments to measure improvements.\nTune ranking functions and hybrid search scoring.\nPartner with product teams to refine search behaviors with real usage patterns.\nRequired Skills & Qualifications\n\n5–10 years of experience in AI/ML, NLP, or IR systems, with hands-on search engineering.\nStrong expertise in ElasticSearch/OpenSearch: analyzers, mappings, scoring, BM25, aggregations, vectors.\nExperience with semantic search:\nEmbeddings (BERT, SBERT, Llama, GPT-based, Cohere)\nVector databases or ES vector fields\nApproximate nearest neighbor (ANN) techniques\nWorking knowledge of LLM-based retrieval and RAG architectures.\nProficient in Python; familiarity with Java/Scala is a plus.\nHands-on AWS experience (OpenSearch, SageMaker, Lambda, ECS/EKS, EC2, S3, IAM).\nExperience building and deploying APIs using FastAPI/Flask and containerizing with Docker.\nFamiliar with typical IR metrics and search evaluation frameworks.\nPreferred Skills\n\nKnowledge of cross-encoder and bi-encoder architectures for re-ranking.\nExperience with query understanding, spell correction, autocorrect, and autocomplete features.\nExposure to LLMOps / MLOps in search use cases.\nUnderstanding of multi-modal search (text + images) is a plus.\nExperience with knowledge graphs or metadata-aware search.","datePosted":"2026-04-14T10:44:02.157Z","dateModified":"2026-04-14T10:44:02.157Z","hiringOrganization":{"@type":"Organization","name":"Software Technology","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Austin","addressRegion":"TX","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"8017dcfe3f293aef7670d55d"},"url":"https://jobsearcher.com/jobs/8017dcfe3f293aef7670d55d"}}