As an AI Engineer at Vendelux, you will research, build, and ship AI-powered product capabilities that improve user workflows, accelerate insights, and drive measurable business value. You'll help establish AI as a foundational layer of the Vendelux product experience, with a focus on agentic systems, LLMs, data, and scalable AI infrastructure.
What You'll Do- Research and apply modern AI methods, including AI agents, LLMs, RAG, embeddings, supervised learning, and unsupervised learning, to power new product capabilities.
- Prioritize impact and speed over perfection when developing and shipping AI-powered solutions.
- Translate business problems into AI solutions that improve user workflows, accelerate insights, and drive measurable value.
- Own the architecture and integration of agentic chat capabilities throughout the Vendelux platform.
- Design the underlying systems that allow AI agents to reason, take action, and surface insights across every surface of the product.
- Establish patterns for how agents interact with internal data, external tools, and user workflows, turning conversational AI from a feature into a foundational layer of the product experience.
- Architect multi-tenant AI infrastructure that meets the performance, latency, and cost requirements of a growing B2B SaaS product.
- Own observability, evaluation frameworks, and guardrails to keep AI features production-grade.
- Work closely with product, data science, and application engineering teams to translate business requirements into AI systems.
- Serve as a thought partner to leadership on the AI roadmap, influencing how Vendelux thinks about product differentiation through AI.
Who You Are- 4+ years of professional experience in software engineering or data engineering, with at least 3+ years building AI/ML-driven products.
- Strong programming skills in Python and proficiency in SQL.
- Experience with modern AI frameworks, such as HuggingFace and LangChain, and designing data pipelines using Airflow, Dagster, or equivalent.
- Solid understanding of cloud-based infrastructure, including AWS, GCP, or Azure.
- Experience applying LLMs and generative AI in production, including prompt engineering, RAG, and LLM deployment.
- Strong grasp of fundamental data science and machine learning techniques, with the ability to balance research and engineering tradeoffs.
- Demonstrated ability to translate business problems into data solutions that drive business value.
- Proven track record of shipping user-facing features with measurable impact.
- Excellent written and verbal communication skills; ability to collaborate across data, engineering, and product teams.
Benefits- Competitive base salary and bonus
- Healthcare covering medical, dental and vision
- Work from our NYC HQ
- Unlimited PTO plus two company-wide shutdowns during the July 4th week and the Christmas - New Years week
Not all candidates will check all of the requirements listed above and that's ok! We are open to great people from non-traditional backgrounds.