SS
Sr. Applied AI/ML Scientist (B2B)
Contract type
Ongoing
Work mode
Remote · Poland
Experience
Senior · 6+ years
Job description
Senior Applied AI/ML Scientist (LLM Applications) at NewsWhip by Sprout Social, building production LLM-powered features such as agentic workflows, retrieval systems, and evaluation frameworks for real-time news intelligence. The role sits in the AI, Data and Intelligence Business Unit.
At a glance
- Employment
- Full-time · Employee (employment agreement)
- Work mode
- Remote · Poland
- Pay
- PLN 26,600 – 33,300 / month
What you'll do
- 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)
- Own the design of LLM-powered content enrichments that feed directly into customer reporting, alerts, and intelligence briefings
- Lead the technical direction for tool-augmented LLM systems, including MCP-compatible services, function-calling patterns, and multi-step reasoning workflows
- 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
- Define structured prompting standards, output schemas, and reusable patterns that the wider engineering team can build on
- Set the bar for how NewsWhip evaluates LLM systems — offline benchmarks, online experimentation, regression detection, and human-in-the-loop review
- Own guardrails for safety, hallucination reduction, factual grounding, and output consistency
- Build observability into every LLM feature: tracing, cost tracking, latency budgets, quality metrics, and drift monitoring
- Make pragmatic trade-offs between model quality, latency, and cost
- Evolve the embedding and semantic search infrastructure, including chunking strategies, hybrid search, and re-ranking
- Improve retrieval relevance as one component of a broader agentic architecture
- Partner with Product and UX to translate ambiguous AI ideas into shipped features
- Lead technical design discussions and represent the AI team in architecture decisions
- Raise the bar through code review, mentorship, and writing
- Evaluate emerging models, frameworks, and techniques and bring the right ones into the stack
What we're looking for
- 6+ years of experience building and operating production software systems
- 2+ years hands-on experience shipping LLM-powered features in real-world applications
- Strong backend engineering skills (Python preferred)
- Experience with several of: Large Language Model APIs (OpenAI, Anthropic, open-weight models, etc.) and transformer-based techniques; embedding models and similarity search; vector databases (ChromaDB, Pinecone, Weaviate, etc.); prompt engineering and structured output techniques; LLM evaluation frameworks and automated testing; LLMOps practices (monitoring, versioning, observability using Langfus
- Track record of owning a system end-to-end in production, not just contributing to one
- Experience making and defending architectural trade-offs (model choice, build vs. buy, latency vs. quality)
- Experience mentoring engineers or leading technical design reviews
- Experience working closely with Product and UX on feature delivery
Nice to have
- Bachelor's in Data Science, Computer Science, Machine Learning, AI, or a related discipline
- Experience with AI orchestration frameworks (LangChain, LlamaIndex, LangGraph, etc.)
- Familiarity with Model Context Protocol (MCP) or tool-calling architectures
- Experience building agentic workflows or tool-using systems
- Knowledge of semantic search and content retrieval systems
- Experience with cloud platforms
- Background in media analytics, content intelligence, or large-scale text processing
- Experience in startup or high-growth environments
Your team
AI, Data and Intelligence Business Unit / Data Science and AI team
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.
Apply
About Sprout Social
NewsWhip by Sprout Social processes the world's news in real time and turns it into predictive intelligence for journalists, PR leaders, and global brands.
Key facts
- Chicago
- NewsWhip is part of Sprout Social
- NewsWhip processes millions of articles, posts, and signals every day
- Kraków office location
- Remote-first model