Senior Applied AI/ML Scientist

Quick Facts

• Role: Senior Applied AI/ML Scientist (Applied AI/ML)

• Focus: Production LLM systems, retrieval, agentic workflows, and evaluation/observability

Description

You will build and ship LLM-powered agentic workflows—both ambient background agents and interactive, tool-using agents—for a real-time news intelligence domain. The role includes owning retrieval and embedding infrastructure, defining structured prompting and output schemas, and setting the bar for evaluation, guardrails, and observability. You’ll lead architecture trade-offs for when to use retrieval, agents, fine-tuning, or classical NLP to meet quality, latency, and cost goals.

Responsibilities

• Build and deliver production LLM-powered agentic workflows (ambient and interactive)

• Design LLM-powered content enrichments feeding customer reporting, alerts, and intelligence briefings

• Lead technical direction for tool-augmented LLM systems, including MCP-compatible services and function-calling patterns

• Decide at architecture level when to use retrieval, agents, fine-tuning, smaller models, or classical NLP

• Define structured prompting standards, output schemas, and reusable patterns

• Set up LLM evaluation with offline benchmarks, online experimentation, regression detection, and human-in-the-loop review

• Implement safety, hallucination reduction, factual grounding, and output consistency guardrails

• Build observability: tracing, cost tracking, latency budgets, quality metrics, and drift monitoring

• Evolve embedding/semantic search infrastructure: chunking, hybrid search, and re-ranking

• Lead cross-functional technical design with Product and UX and influence AI roadmap

• Mentor engineers and raise quality through code review, design reviews, and writing

• Evaluate emerging models/frameworks and bring improvements into the stack

Requirements

• 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 LLM APIs and transformer-based techniques

• Experience with embeddings and similarity search

• Experience with vector databases

• Prompt engineering and structured output techniques

• LLM evaluation frameworks and automated testing

• LLMOps practices including monitoring, versioning, and observability

• Ability to own a system end-to-end in production

• 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

Benefits

• Stock ownership (RSUs)

• Generous paid time off (26 paid days annually plus bank holidays and additional rest days)

• Paid parental leave (20 weeks birthing parents, 16 weeks non-birthing parents)

• Lifestyle Spending Account ($600 USD annually)

• Remote-first with support for home office setup and monthly internet reimbursement

• Mental health resources and wellness programs

• International travel opportunities for team meetups

• Kraków office perks (daily lunch stipend when working from office)

• Salary transparency with net monthly ranges and performance-based growth opportunities

• Interview accommodations support and flexible work location within Poland