EngineerJobs.io
← Back to all jobs

Job Description

Build AI-powered product capabilities at scale. Vendelux is looking for a Staff AI Engineer in Arlington, VA (onsite) to research and ship AI and LLM capabilities that deliver measurable value. In this role, you will help evolve conversational experiences into a foundational product layer, while designing multi-tenant AI infrastructure that supports performance, reliability, and cost targets for a growing B2B SaaS platform.

You will work across the stack from modern AI methods to production-ready systems, including agentic chat across the Vendelux platform and the data and infrastructure that make those capabilities dependable for real users.

Responsibilities

  • Research and apply modern approaches such as AI agents, LLMs, RAG, embeddings, and supervised/unsupervised learning to deliver new product capabilities, prioritizing impact and speed over perfection.
  • 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, including the underlying systems that let agents reason, take action, and surface insights across product surfaces.
  • Define patterns for how agents interact with internal data, external tools, and user workflows, turning conversational AI into a core product experience.
  • Architect multi-tenant AI infrastructure to meet performance, latency, and cost requirements as the B2B SaaS product grows.
  • Own observability, evaluation frameworks, and guardrails to keep AI features production-grade.
  • Collaborate with product, data science, and application engineering teams to convert business requirements into AI systems.
  • Act as a thought partner to leadership on the AI roadmap, shaping how Vendelux differentiates through AI.

Requirements

  • 8+ years of professional experience in software engineering or data engineering, with 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, plus designing data pipelines using Airflow, Dagster, or equivalents.
  • Solid understanding of cloud infrastructure such as AWS, GCP, or Azure.
  • Production experience applying LLMs and generative AI, including prompt engineering, RAG, and LLM deployment.
  • Strong grasp of core data science and machine learning techniques, with the ability to balance research and engineering tradeoffs.
  • Ability to translate business problems into data solutions that drive business value.
  • Demonstrated track record shipping user-facing features with measurable impact.
  • Excellent written and verbal communication skills and experience collaborating across data, engineering, and product teams.
  • Startup experience preferred.

Technologies: Python, SQL, HuggingFace, LangChain, Airflow, Dagster, AWS, GCP, Azure, LLMs, RAG, embeddings, AI agents

Similar Jobs