Lead/Staff Engineer - Applied AI

About the role

We're seeking a seasoned Engineer to lead the development of LLM-powered AI agents and next-gen Generative AI systems that drive core product functionality and customer-facing automation at scale. This is a high-autonomy, high-impact role for someone who thrives at the intersection of applied AI, agent design, and core data science.

What you'll do

• Architect and deploy autonomous AI agents that execute workflows across sales, messaging, scheduling, and operations
• Develop robust retrieval-augmented generation (RAG) systems and vector search infrastructure to enable context-rich, real-time generation
• Design and iterate on prompt engineering, context construction, and agent tool usage strategies using frameworks like LangChain
• Apply core data science methods — modeling, A/B testing, scoring, clustering, and time-series forecasting — to enhance agent intelligence and broader product features
• Partner with backend, infra, and product teams to build reusable, scalable GenAI infrastructure: model serving, prompt versioning, logging, evals, and feedback loops

What you need

• 9–16 years in data science & ai
• Machine learning
• LLMs
• Python
• Prompt engineering
• AWS
• MLOps
• Any graduate

Good to have

• PyTorch
• GCP
• CI/CD
• TypeScript