Description

You will architect and build scalable AI-native products, moving from 0-to-1 through full production scale.

This role is on-site.

Responsibilities

• Design agentic systems using frontier LLMs (Claude, GPT), implementing tool calling, multi-step orchestration, and memory management.
• Build production RAG pipelines, including embeddings, vector search, chunking, re-ranking, and semantic grounding over enterprise data.
• Engineer prompts and context windows, ensuring structured JSON output, schema validation, and robust evaluation harnesses.
• Develop async backend services and modern frontend interfaces using Python and JavaScript/TypeScript (React/Vite).
• Deploy and manage infrastructure across Azure, AWS, and GCP using containers and cloud-native patterns.

Required Skills

• 15+ years of software engineering experience with a proven track record of shipping products at scale.
• Deep expertise in LLM engineering, including agent skills, function calling, and latency/cost trade-offs.
• Strong proficiency in Python and modern JS/TS (React, Vite).
• Experience with cloud platforms (Azure, AWS, GCP) and containerization.
• Knowledge of graph or semantic data modeling.
• Bachelor's or Master's degree in a relevant field.

Preferred Skills

• Experience with CPQ, quote-to-cash workflows, or enterprise SaaS.
• Familiarity with Salesforce or Revenue Cloud.

Key Skills

Education

Bachelor's or Master's degrees