The Opportunity
Stonly is an AI knowledge platform for customer service. Our SaaS platform helps companies (DraftKings, King, Estēe Lauder, Personio, and many more) automate their customer service with AI and interactive knowledge delivered at the point of need for both agents and customers.
The company was created 6 years ago by Alexis (former co-founder and CPO of Dashlane), David (ex VP sales and marketing at Calendly) & Krzysztof (ex Dashlane)
Stonly is a global company with offices in Poland, France, & the US. We’ve raised over $22m in 2022 with top VC funds Accel & NorthZone. Our ambition is huge: to become the leading knowledge platform for customer service - a $50 billion market - and become an iconic tech brand in the space.
We are seeking a versatile and talented Applied AI Engineer / Researcher to join our core team. This is a unique hybrid role for someone who thrives at the intersection of applied research and production-grade software engineering. You will be instrumental in designing, building, and deploying our next-generation AI solutions, with a strong focus on Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG).
The ideal candidate has a deep interest in modern AI and is passionate about turning state-of-the-art research into tangible product impact. What makes this role particularly unique is the blend of deep AI expertise with practical software engineering, including the opportunity to work within our JavaScript/TypeScript environment. You will own ML systems end-to-end, from prototype to production, and collaborate closely with founders and product leaders.
What You’ll Do?
Design & Develop: Design, build, and deploy advanced NLP and Generative AI solutions, focusing on Information Retrieval, RAG, and Agentic RAG pipelines for applications like document processing and intelligent assistants.
Research & Innovate: Conduct scientific literature reviews, evaluate third-party models, and design internal benchmark datasets from scratch to validate and improve our solutions.
Build & Operate: Build, deploy, and maintain robust, scalable, and low-latency model-serving infrastructure in a cloud-native environment (AWS/Azure).
Monitor & Optimize: Define and monitor key production metrics, troubleshoot AI systems, and continuously improve performance, reliability, and safety (e.g., implementing guardrails and prompt-injection defenses).
Integrate & Collaborate: Work with our engineering team to implement scalable JS/TypeScript microservices that expose ML models via APIs. You will collaborate closely with product, research, and platform teams to transform proofs-of-concept into secure, maintainable production code.
Core Qualifications & Skills (Who You Are):
Strong theoretical foundation in Machine Learning, Deep Learning, and NLP concepts.
Proven experience in designing and implementing NLP solutions, particularly with Information Retrieval algorithms (RAG, Agentic RAG).
Deep, hands-on experience with Large Language Models (LLMs), including prompt engineering, embeddings, hybrid search, and vector databases.
Ability to move fast with Python for AI/ML for vibe codded apps At least a basic understanding of and willingness to work with JavaScript/TypeScript.
Experience building and maintaining ML model-serving infrastructure, including monitoring and observability.
Proficiency in SQL for large-scale data analysis and feature engineering.
Excellent communication and collaboration skills, with experience working in cross-functional teams.
Nice-to-Haves (Bonus Points):
Experience deploying and operating ML systems at scale with high-throughput and low-latency requirements.
Familiarity with LLM safety techniques, such as guardrails and prompt-injection defense.
Practical experience implementing scalable microservices in JS/TypeScript that expose ML models.
Experience with web crawling, parsing, and knowledge-base construction.
A proactive mindset, with a passion for initiating innovative solutions and driving continuous improvement.
Willingness to participate in ensuring high system availability, including on-call duty rotations.
Working at Stonly
Core Values & Culture: We care deeply about our customers, our business growth, and each team member’s career and success. We prioritize team-building, collaboration, working with people we enjoy and who push us to become better.
Flexible Contract Options: Choose between an employment contract or a B2B contract based on your preference.
Equity Opportunities: Equity options are included as part of your compensation package.
Prime Office Location: Work from our office in the heart of Kraków.
Comprehensive Healthcare: Enjoy private healthcare for your peace of mind.
Fitness Perks: Access to a Multisport card to support your fitness goals.
Flat Organizational Structure: Experience a non-hierarchical environment that promotes direct communication and collaboration.
What does our recruitment process look like?
You will first have a general chat with Aneta our Talent Acquisition Manager (45 min)
You’ll then work on a task and discuss it with Wojtek (our Lead Server Engineer) during the technical meeting (1,5 h)
You’ll then have a conversation with Alexis (CEO and co-founder) (30min)
Stonly provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state, or local laws.
This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, and training.