<p><span style="font-size: 10pt;"><strong>Description</strong></span></p> <p><span style="font-size: 10pt;">NewsWhip by Sprout Social is looking for a <strong>Senior Applied AI/ML Scientist </strong>to join its AI, Data and Intelligence Business Unit. </span></p> <p><span style="font-size: 10pt;"><strong>Why join NewsWhip by Sprout Social’s Data Science and AI team? </strong></span></p> <p><span style="font-size: 10pt;">Most LLM applications are wrappers around a chat box. Ours aren't. </span></p> <p><span style="font-size: 10pt;">NewsWhip processes the world's news in real time - millions of articles, posts, and signals every day - and turns that firehose into predictive intelligence that journalists, PR leaders, and global brands rely on to make decisions before the news breaks. The interesting problems live everywhere in that pipeline: ambient agents that monitor and enrich content as it flows in, retrieval systems that have to be fast and correct on a corpus that changes by the minute, evaluation frameworks for a domain where hallucination has real-world consequences, and reporting workflows where LLM-generated insights need to stand up to scrutiny by professional analysts.</span></p> <p><span style="font-size: 10pt;">You'll work at the intersection of product, data, and engineering with the autonomy to make architectural decisions and the support of a company that takes AI quality seriously. If you want to build LLM systems that do more than answer questions - systems that reason, retrieve, enrich, and act across one of the most demanding content domains there is — this is the role.</span></p> <p><span style="font-size: 10pt;">What you'll do</span></p> <p><span style="font-size: 10pt;">Build and Ship LLM-Powered Features</span></p> <ul> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Architect and deliver production agentic workflows — both ambient (background agents that enrich, monitor, summarise, and surface insights across NewsWhip's data continuously) and interactive (user-facing tool-using agents that respond to journalist and PR analyst queries in real time).</span></p> </li> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Own the design of LLM-powered content enrichments that feed directly into customer reporting, alerts, and intelligence briefings — turning raw news signals into structured, decision-ready outputs.</span></p> </li> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Lead the technical direction for tool-augmented LLM systems, including MCP-compatible services, function-calling patterns, and multi-step reasoning workflows.</span></p> </li> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Make architecture-level decisions about when to use retrieval, when to use agents, when to fine-tune, and when a smaller model or classical NLP approach is the right answer.</span></p> </li> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Define structured prompting standards, output schemas, and reusable patterns that the wider engineering team can build on.</span></p> </li> </ul> <p><span style="font-size: 10pt;">Drive Quality, Evaluation, and Observability</span></p> <ul> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Set the bar for how NewsWhip evaluates LLM systems — offline benchmarks, online experimentation, regression detection, and human-in-the-loop review.</span></p> </li> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Own guardrails for safety, hallucination reduction, factual grounding, and output consistency in a domain (news and media intelligence) where accuracy is non-negotiable.</span></p> </li> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Build observability into every LLM feature: tracing, cost tracking, latency budgets, quality metrics, and drift monitoring.</span></p> </li> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Make pragmatic trade-offs between model quality, latency, and cost — and be accountable for them.</span></p> </li> </ul> <p><span style="font-size: 10pt;">Retrieval, Embeddings, and Semantic Infrastructure</span></p> <ul> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Evolve the embedding and semantic search infrastructure that underpins NewsWhip's intelligence layer, including chunking strategies, hybrid search, and re-ranking.</span></p> </li> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Improve retrieval relevance as one component of a broader agentic architecture — not as an end in itself.</span></p> </li> </ul> <p><span style="font-size: 10pt;">Lead Technically and Influence Cross-Functionally</span></p> <ul> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Partner with Product, and UX to translate ambiguous AI ideas into shipped features customers actually rely on.</span></p> </li> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;">Lead technical design discussions and represent the AI team in architecture decisions.</span></p> </li> <li style="font-size: 10pt;"> <p><span style="font-size: 10pt;"&g