{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/speech-transcription"},"x-facet":{"type":"skill","slug":"speech-transcription","display":"Speech Transcription","count":1},"x-feed-size-limit":100,"x-feed-sort":"enriched_at desc","x-feed-notice":"This feed contains at most 100 jobs (the most recently enriched). For the full corpus, use the paginated /stats/by-facet endpoint or /search.","x-generator":"yubhub-xml-generator","x-rights":"Free to redistribute with attribution: \"Data by YubHub (https://yubhub.co)\"","x-schema":"Each entry in `jobs` follows https://schema.org/JobPosting. YubHub-native raw fields carry `x-` prefix.","jobs":[{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_859c75b7-6fc"},"title":"Engineering Manager, Multimodal (API)","description":"<p>We are seeking an Engineering Manager to lead our multimodal API product suite. Your team will be responsible for delivering innovative APIs across real-time processing, speech transcription, speech generation, and image creation.</p>\n<p>You will own the product roadmap for how we evolve our multimodal API offerings, and you will build the products that allow developers to reach millions of end users through AI audio, video, and images.</p>\n<p><strong>Responsibilities</strong></p>\n<ul>\n<li>Build, mentor, and grow a high-performing engineering team focused on multimodal API products – including our real-time API, our transcription models (Whisper), our speech generation models (TTS), and our image generation APIs (DALLE and native 4o).</li>\n<li>Collaborate closely with product managers, designers, and other stakeholders to define the strategic vision and product roadmap.</li>\n<li>Work closely with our research teams to improve our core multimodal models for API customer use cases.</li>\n<li>Guide technical and architectural decisions, emphasizing scalability, robustness, and user experience.</li>\n<li>Foster a culture of innovation, continuous improvement, and accountability within your team.</li>\n</ul>\n<p><strong>Qualifications</strong></p>\n<ul>\n<li>Proven experience managing engineering teams that deliver complex, high-quality products at scale.</li>\n<li>Strong technical background and proficiency in modern software engineering practices and system architecture.</li>\n<li>Excellent collaboration and communication skills to effectively coordinate across diverse teams and stakeholders.</li>\n<li>Familiarity with or strong interest in multimodal AI, including speech technologies, real-time systems, and image generation.</li>\n<li>Ability to operate effectively in a fast-paced, ambiguous startup environment.</li>\n</ul>\n<p><strong>Preferred Qualifications</strong></p>\n<ul>\n<li>Experience developing multimodal systems or APIs in AI/ML domains, especially around image generation, audio generation, or speech transcription.</li>\n<li>Familiarity with real-time streaming technologies, audio processing, and computer vision.</li>\n<li>Hands-on experience with cloud platforms and distributed architectures.</li>\n</ul>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_859c75b7-6fc","directApply":true,"hiringOrganization":{"@type":"Organization","name":"OpenAI","sameAs":"https://openai.com/","logo":"https://logos.yubhub.co/openai.com.png"},"x-apply-url":"https://jobs.ashbyhq.com/openai/1d7f4747-54a3-4141-a39a-c6e7700e969b","x-work-arrangement":"onsite","x-experience-level":"mid","x-job-type":"Full time","x-salary-range":"$293K – $385K","x-skills-required":["multimodal AI","speech technologies","real-time systems","image generation","cloud platforms","distributed architectures"],"x-skills-preferred":["audio generation","speech transcription","real-time streaming technologies","audio processing","computer vision"],"datePosted":"2026-04-24T12:18:02.815Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"multimodal AI, speech technologies, real-time systems, image generation, cloud platforms, distributed architectures, audio generation, speech transcription, real-time streaming technologies, audio processing, computer vision","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":293000,"maxValue":385000,"unitText":"YEAR"}}}]}