Senior Applied AI/ML Scientist – B2B

• Architect and deliver production ambient and interactive agentic workflows
• Design LLM-powered content enrichments for customer reporting, alerts, and intelligence briefings
• Lead technical direction for MCP-compatible services, function-calling patterns, and multi-step reasoning workflows
• Make architecture decisions about retrieval, agents, fine-tuning, smaller models, and classical NLP
• Define structured prompting standards, output schemas, and reusable engineering patterns
• Establish LLM evaluation practices including offline benchmarks, online experimentation, regression detection, and human-in-the-loop review
• Own safety, hallucination reduction, factual grounding, and output consistency guardrails
• Build observability through tracing, cost tracking, latency budgets, quality metrics, and drift monitoring
• Balance model quality, latency, and cost
• Evolve embedding and semantic search infrastructure, including chunking, hybrid search, and re-ranking
• Improve retrieval relevance within broader agentic architectures
• Partner with Product and UX to ship customer-facing AI features
• Lead technical design discussions and represent the AI team in architecture decisions
• Raise engineering standards through code review, mentorship, and writing
• Evaluate emerging models, frameworks, and techniques and incorporate appropriate options into the stack
• Drive end-to-end delivery of significant AI features from concept through production
• Establish reusable tooling and patterns to improve LLM development velocity and reliability
• Mentor engineers on prompt design, evaluation, and AI system reliability

• 6+ years of experience building and operating production software systems
• 2+ years of 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 and transformer-based techniques; embedding models and similarity search; vector databases such as ChromaDB, Pinecone, or Weaviate; prompt engineering and structured output techniques; LLM evaluation frameworks and automated testing; LLMOps practices including monitoring, versioning, and observability using Langfuse or Datadog
• Track record of owning a system end-to-end in production
• Experience making and defending architectural trade-offs, including model choice, build vs. buy, and latency vs. quality
• Experience mentoring engineers or leading technical design reviews
• Experience working closely with Product and UX on feature delivery
• Bachelor’s degree in Data Science, Computer Science, Machine Learning, AI, or a related discipline preferred
• Experience with AI orchestration frameworks such as LangChain, LlamaIndex, or LangGraph preferred
• Familiarity with Model Context Protocol (MCP) or tool-calling architectures preferred
• Experience building agentic workflows or tool-using systems preferred
• Knowledge of semantic search and content retrieval systems preferred
• Experience with cloud platforms preferred
• Background in media analytics, content intelligence, or large-scale text processing preferred
• Experience in startup or high-growth environments preferred

• Eligibility for Restricted Stock Units (RSUs)
• 26 paid days off annually, in addition to bank holidays and extra company-wide "Rest & Recharge" days
• 20 weeks of paid leave for birthing parents
• 16 weeks of paid leave for non-birthing parents
• Annual $600 USD Lifestyle Spending Account for personal well-being, gym memberships, health expenses, hobbies, or wellness needs
• Flexible, remote-first model
• One-time $550 USD home office setup stipend
• Monthly internet reimbursement
• Dedicated mental health resources
• Company-wide wellness programs
• Opportunities to travel to Chicago HQ for team meetups and collaboration
• Daily 50 zł lunch stipend when working from the Kraków office