Build and Ship LLM-Powered Features

• 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 — turning raw news signals into structured, decision-ready outputs.
• 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.

Drive Quality, Evaluation, and Observability

• 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 in a domain (news and media intelligence) where accuracy is non-negotiable.
• 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 — and be accountable for them.

Retrieval, Embeddings, and Semantic Infrastructure

• Evolve the embedding and semantic search infrastructure that underpins NewsWhip's intelligence layer, including chunking strategies, hybrid search, and re-ranking.
• Improve retrieval relevance as one component of a broader agentic architecture — not as an end in itself.

Lead Technically and Influence Cross-Functionally

• Partner with Product, and UX to translate ambiguous AI ideas into shipped features customers actually rely on.
• Lead technical design discussions and represent the AI team in architecture decisions.
• Raise the bar through code review, mentorship, and writing — help less experienced engineers grow into strong AI practitioners.
• Stay close to the frontier: evaluate emerging models, frameworks, and techniques and bring the right ones into the stack.

What you’ll bring

We’re looking for an experienced and highly technical Senior Applied AI/ML Scientist who embraces challenges, practices a growth mindset, and is eager to collaborate with a variety of stakeholders to provide data-driven solutions to business leaders and to NewsWhip’s by Sprout Social customers.

Minimum Qualifications

• 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 the following:
• 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 Langfuse, Datadog, etc.)
• 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.

Preferred Qualifications

• 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.

How you’ll grow

• Complete onboarding and gain a deep understanding of NewsWhip’s product, data model, and AI roadmap.
• Meet and learn from assigned onboarding resources.
• Set clear expectations and goals with your manager.
• Familiarize yourself with our existing LLM infrastructure, evaluation practices, and vector systems.
• Ship your first meaningful improvement or feature iteration to production.
• Become familiar with our existing features, available data, and best practices.

• Take ownership of a core LLM-powered feature or subsystem.
• Implement measurable improvements to prompt quality, retrieval relevance, or model performance.
• Contribute to improving our AI evaluation and testing strategy.
• Lead at least one technical design discussion related to AI architecture.

• Drive the end-to-end delivery of a significant AI feature from concept to production launch.
• Establish reusable patterns or tooling that improve LLM development velocity and reliability.
• Demonstrate measurable impact on quality metrics (e.g., reduced hallucination rates, improved relevance, latency, or cost efficiency).

• Be recognized as a go-to expert for LLM systems and applied AI best practices within the team.
• Help shape the longer-term AI architecture and technical roadmap.
• Mentor other engineers on prompt design, evaluation, and AI system reliability.
• Surprise us - propose and deliver AI innovations that meaningfully change how customers use NewsWhip.

Of course what is outlined above is the ideal timeline, but things may shift based on business needs and other projects and tasks could be added at the discretion of your manager.

Our Benefits Program

We’re proud to regularly be recognized for our team, product and culture. Our benefits program includes:

• Stock Ownership (RSUs): Eligibility for Restricted Stock Units (RSUs)
• Generous Paid Time Off: 26 paid days off annually, in addition to bank holidays and extra company-wide "Rest & Recharge" days.
• Paid Parental Leave: We support all growing families with 20 weeks of paid leave for birthing parents and 16 weeks of paid leave for non-birthing parents.
• Lifestyle Spending Account (LSA): An annual $600 USD fund to support your personal well-being. This can be used for gym memberships, health expenses, hobbies, or other wellness needs.
• Remote & Hybrid Work Support: A flexible, remote-first model supported by a one-time $550 USD home office setup stipend and a monthly internet reimbursement.
• Mental Health & Well-being: Access to dedicated mental health resources and company-wide wellness programs.
• International Travel: Opportunities to travel to our Chicago HQ for team meetups and collaboration.
• Kraków Office Perks: A daily 50 zł lunch stipend when you choose to work from our office.
• This list is for informational purposes only. Benefit offerings are discretionary and subject to change and do not constitute a contract or guarantee of benefits.

Our salary ranges reflect the expected earning potential for this role. Individual pay is based on geographic zone, relevant experience, and skills.

Our current hiring range for this role: 26,600 PLN - 33,300 PLN Net monthly. Offers are made within this range, with opportunities to grow within the broader band based on performance and impact.

We share both our current hiring range and our broader geographic salary bands to provide transparency into our compensation philosophy. This ensures you understand not only your starting potential but also the long-term growth opportunities available as you progress in your role.

The full base pay range for this role is PLN 26,600 PLN – 40,000 PLN Net monthly.

These ranges were determined by a market-based compensation approach; we used data from trusted third-party compensation sources to set equitable, consistent, and competitive ranges. We also evaluate compensation bi-annually, identify any changes in the market and make adjustments to our ranges and existing employee compensation as needed.

Whenever possible, we want to provide team members the flexibility to work in the location that makes the most sense for them. If you prefer an office setting, this role may be based in our Kraków location. If you prefer to work remotely from another location within Poland, we will accommodate you as best as possible.

#LI-REMOTE