Staff AI Engineer — Lead LLMs & AI Platform Architect

Vendelux; Arlington (VA); On-site; USD 180,000 - 240,000; Full time

Job summary

Vendelux is hiring a Staff AI Engineer in Arlington, VA (onsite) to research and deliver AI and LLM-powered product capabilities across the platform. You will own architecture for agentic chat and multi-tenant AI infra to scale our B2B SaaS offering.

You will translate business challenges into AI solutions, balance research and engineering tradeoffs, and collaborate with product, data science, and application engineering teams to ship user-facing features with measurable impact.

Qualifications

• 8+ years of professional software/data engineering experience.
• Strong Python and SQL proficiency.
• Experience with HuggingFace, LangChain, and data pipelines.
• Cloud infrastructure knowledge across AWS, GCP or Azure.
• Production experience with LLMs, prompts, RAG and deployment.
• Ability to translate business problems into data solutions.

Responsibilities

• Research and apply modern AI methods (AI agents, LLMs, RAG, embeddings) to enable new product capabilities with emphasis on impact and speed.
• Convert business challenges into AI solutions that improve user workflows, insights, and measurable value.
• Own architecture and integration of agentic chat across Vendelux platform for reasoning, action, and insights.
• Define interaction patterns for agents with internal data, external tools, and user workflows.
• Architect multi-tenant AI infrastructure to meet performance, latency, and cost needs for a growing B2B SaaS product.
• Own observability, evaluation frameworks, and guardrails to keep AI features production-grade.
• Collaborate with product, data science, and application engineering to translate requirements into AI systems.
• Advise leadership on the AI roadmap and differentiation through AI.

Skills

Python

SQL

AI/ML

Communication

Tools

HuggingFace

LangChain

Airflow

Dagster

AWS

GCP

Azure

Job description

Vendelux is hiring a Staff AI Engineer in Arlington, VA (onsite) to research and deliver AI and LLM-powered product capabilities across the platform. You will own architecture for agentic chat and multi-tenant AI infra to scale our B2B SaaS offering.

You will translate business challenges into AI solutions, balance research and engineering tradeoffs, and collaborate with product, data science, and application engineering teams to ship user-facing features with measurable impact.