Staff Software Engineer - Konnect AI Platform

📋 Description

• • Are you a visionary Staff Software Engineer with a passion for building the foundational infrastructure that powers cutting-edge AI capabilities? Do you thrive on architecting robust, scalable, and privacy-conscious data pipelines that fuel intelligent systems? If so, Kong Inc. is looking for you to join our dynamic AI Platform team as a Staff Software Engineer in Bangalore, India.
• • At Kong, we are at the forefront of API and AI connectivity, building the infrastructure that defines the agentic era. Our unified platform, Kong Konnect, is trusted by leading organizations worldwide to secure, manage, accelerate, govern, and monetize the flow of intelligence across APIs and AI models. As a Staff Software Engineer on the AI Platform team, you will play a pivotal role in shaping the future of AI at Kong by developing the sophisticated data pipelines, knowledge systems, and vector search infrastructure that underpin our advanced AI functionalities.
• • This is a unique opportunity to make a significant impact by building the very data foundation that enables our AI capabilities. You will be instrumental in developing systems for documentation ingestion, enabling powerful semantic search, creating efficient embedding pipelines, and managing our knowledge bases. Your work will directly influence the accuracy, relevance, and privacy compliance of the AI-driven insights and services we provide to our customers. We are seeking individuals who possess a deep understanding of vector databases, embedding models, advanced document processing techniques, and robust MLOps practices. Your expertise will ensure that our AI systems have access to high-quality, privacy-compliant data, empowering them to deliver precise and contextually relevant responses.
• • Your responsibilities will span the entire lifecycle of data for AI, from initial ingestion to ongoing monitoring and optimization. You will be tasked with designing and implementing sophisticated documentation ingestion pipelines, specifically tailored for AWS Bedrock Knowledge Base and other leading vector stores. A key aspect of your role will involve building advanced semantic chunking and document processing systems, meticulously optimized to enhance retrieval quality and preserve crucial context. Furthermore, you will develop cutting-edge vector embedding pipelines, incorporating hybrid search strategies that seamlessly blend semantic understanding with keyword relevance, ensuring comprehensive and accurate search results.
• • To ensure the continuous improvement and reliability of our AI systems, you will create real-time telemetry collection systems for comprehensive model monitoring, performance tracking, and rigorous quality assurance. Data privacy is paramount; therefore, you will implement robust data anonymization and PII detection systems to guarantee that all AI operations are conducted in strict adherence to privacy regulations. Maintaining the freshness and integrity of our knowledge bases will be achieved through the development of automated knowledge base refresh and quality monitoring systems.
• • Your contributions will extend to designing and implementing feature stores, crucial for managing model inputs, prompt variables, and contextual information efficiently. You will also develop sophisticated training data curation pipelines, laying the groundwork for future fine-tuning and model improvement initiatives. Optimizing vector indexes and database performance for low-latency retrieval at scale will be a critical focus, ensuring our systems can handle demanding workloads. To further enhance search relevance, you will create metadata enrichment and entity extraction pipelines.
• • Embracing real-time data processing, you will build streaming data pipelines for immediate data ingestion and processing. Collaboration is key; you will work closely with AI engineers to refine retrieval strategies and elevate the performance of our Retrieval Augmented Generation (RAG) systems. Establishing and championing best practices for data quality, privacy compliance, and GDPR-compliant data handling will be integral to your role. Finally, you will partner with platform engineers to ensure the seamless deployment and scalable operation of our data infrastructure on AWS, leveraging the full power of cloud-native solutions.
• • This role demands a proactive, detail-oriented engineer who is passionate about solving complex data challenges and driving innovation in the AI space. If you are eager to contribute to a world-class AI platform and shape the future of intelligent connectivity, we encourage you to apply.