Job Description
STAFF APPLIED AI ENGINEER (LLMs, RAG, EVALUATION)
SAN FRANCISCO BAY AREA — HYBRID
$225,000 – $250,000 BASE + EQUITY
The Opportunity
We’re building AI systems that solve complex, real-world problems—including recommendation systems, object mapping, and knowledge graph-driven workflows—where there’s no clear playbook.
This role sits at the intersection of ML research, experimentation, and production engineering. You’ll define approaches from scratch, validate them through data, and ship scalable systems in production.
What You’ll Do
- Build and scale LLM + RAG systems, including recommendation workflows
- Design evaluation frameworks (datasets, metrics, tradeoffs)
- Run experiments to understand what works—and why
- Develop production systems in Python
- Work across: recommendation systems, object/entity mapping, & knowledge graphs
- Balance accuracy, latency, and cost
What We’re Looking For
- 8–12+ years in AI/ML with strong ownership
- Background typically: Data Scientist → ML/AI Engineer
- Experience with:
- LLMs, RAG, and recommendation systems in production
- evaluation, experimentation, and metrics design
- Strong analytical mindset—able to diagnose failures and iterate
- Solid Python + production engineering skills
- Comfortable working in ambiguous problem spaces
Tech Stack
- Python
- LLM APIs
- RAG pipelines
- Vector search
- Recommendation systems
- SQL
- Cloud (AWS/GCP)
Why Join
- Work on high-impact AI systems (including recommendations) with no predefined approach
- Own the full lifecycle: idea → experiment → production
- Help shape next-generation systems like knowledge graphs and intelligent recommendation engines
Bottom Line
A role for someone who enjoys solving ambiguous ML problems, rigorously evaluating them, and building production AI systems that drive real-world decisions.