Senior IA Engineers

Join a diverse team of approx. 2000 professionals across four continents, driving innovation and growth within intive’s technology hubs. Work alongside industry experts trusted by leading brands like Audi, BMW, Deichmann, Meta, NewsCorp, Tandem, Paramount, Vorwerk, and Warner Bros. Discovery to create pioneering, sustainable digital experiences.

At intive, agile thinking and deep industry expertise come together across Automotive & Mobility, Commerce, Financial Services, Healthcare & Life Sciences, and Technology, Media & Communication. Be part of a team that’s shaping the future of digital innovation.

What You Will Be Doing

• Design, build, and optimize large-scale search and retrieval platforms.
• Develop backend services and APIs using Python frameworks such as FastAPI or Flask.
• Build and maintain ETL and data ingestion pipelines.
• Implement semantic search, vector search, KNN retrieval, and Retrieval-Augmented Generation (RAG) solutions.
• Design and optimize retrieval strategies, including reranking, query decomposition, and document chunking.
• Work across Python and Node.js/TypeScript ecosystems to deliver scalable backend solutions.
• Develop and maintain asynchronous and event-driven ingestion pipelines using messaging and streaming technologies.
• Manage and optimize OpenSearch/Elasticsearch clusters, indexes, mappings, and search performance.
• Deploy, operate, and troubleshoot cloud-native solutions within AWS environments.
• Monitor, debug, and optimize production systems to ensure reliability, scalability, and performance.

You Are a Good Match If You Have

• 8+ years of backend engineering experience building distributed, high-performance systems.
• Strong hands-on experience with Python for backend services and ETL/data pipelines.
• Experience developing APIs and services using FastAPI and/or Flask.
• Proven experience working within mixed Python and Node.js/TypeScript ecosystems.
• Advanced expertise with OpenSearch and/or Elasticsearch, including mappings, sharding strategies, DSL queries, tokenizers/analyzers, and cluster management.
• Experience implementing semantic search solutions, embeddings, vector search, KNN retrieval, and RAG architectures.
• Hands-on experience with LlamaIndex or similar retrieval/RAG frameworks.
• Ability to implement retrieval optimization techniques such as reranking, query decomposition, and document chunking strategies.
• Solid experience with Node.js and TypeScript for backend and API integrations.
• Strong AWS experience, including Lambda, ECS, Managed OpenSearch, and ALB/NLB.
• Strong troubleshooting, debugging, and performance optimization skills in production environments.
• Experience building asynchronous and event-driven ingestion pipelines using technologies such as SQS, Kafka, SNS, or RabbitMQ.
• Experience with unit testing frameworks and validation strategies across JavaScript/TypeScript and Python-based systems.

Nice to Have

• Experience processing and indexing millions of documents at scale.
• Experience building search platforms with sub-second query latency requirements.
• Experience integrating with OpenAI, Anthropic, AWS Bedrock, or Vertex AI.
• Understanding of embedding model selection, evaluation methodologies, and performance tradeoffs.
• Experience with NLP and text-processing libraries such as NumPy, NLTK, or similar.
• Experience implementing Small-to-Big retrieval patterns.
• Experience designing observability and monitoring solutions for search platforms and data pipelines.
• Background in AI-powered search, enterprise search, media platforms, legal technology, or knowledge management systems.
• Experience with observability tools such as Datadog, OpenTelemetry, New Relic, Grafana, or CloudWatch.