Applied AI Scientist

The role

You will work on hard reasoning, retrieval, and orchestration problems to ship research-informed product work. You will design grounding and context assembly, improve orchestration across multi-step workflows, and build structured representations for system reasoning.

What you will do

• Design grounding and context assembly including retrieval pipelines, context selection, and query understanding
• Improve orchestration and reasoning across multi-step workflows including tool use, routing, decomposition, and evaluation
• Build structured representations that help the system reason over accounts, people, and activity
• Translate research-grade rigor into reliable, production-ready capabilities
• Write real code that holds up in production
• Raise technical rigor by sharing patterns, mentoring, and accelerating decisions across teams

Required qualifications

• PhD in CS, ML, NLP, IR, or a related field
• 7+ years in applied ML, NLP, IR, or ranking
• Recent hands-on ownership of LLM and agentic systems
• Shipped LLM or RAG-style systems into production
• Personally owned reliability, latency, and monitoring at scale for shipped systems
• Built and owned agentic or multi-step orchestration
• Strong coding ability and real comfort in a production codebase
• Solid experimentation and evaluation rigor including offline evals, A/B testing, and causal thinking
• IC5 signals including setting technical direction across teams, owning architecture, and operating as a peer-level influence

Nice to have

• Knowledge graphs, entity resolution, or representation learning
• Query understanding and intent modeling
• Search and retrieval depth: lexical, semantic, hybrid, reranking
• LLM fine-tuning
• A record of taking research from idea to published result to shipped feature

About the company

Demandbase is a pipeline AI platform that empowers GTM teams to automate growth at scale. The company has offices in San Francisco, New York, Austin, Seattle, India, and the United Kingdom.