What are the responsibilities and job description for the VP AI/ML Software Engineer – Agentic AI / LLM Systems - Fulltime position at PURVIEW?
Hiring: Senior AI Software Engineer(Vice President) – Agentic AI / LLM Systems
Locations: Jersey City, NJ | Dallas, TX | Menlo Park, CA | Seattle, WA (Onsite)
Duration: Full-Time
Work Authorization (IMPORTANT):
• Must be authorized to work in the U.S. on a full-time basis
• Unable to sponsor new visas at this time
We’re hiring a hands-on AI Software Engineer to build and deploy production-grade agentic AI systems using LLMs. This is a deeply technical individual contributor role focused on engineering, not architecture or leadership.
What You’ll Do:
• Design and build multi-agent AI systems (planning, reasoning, tool usage)
• Develop backend services & APIs for AI-driven applications
• Build and deploy RAG pipelines and LLM-powered systems
• Integrate AI with observability, monitoring, and production workflows
• Deploy and scale systems using Docker, Kubernetes, and cloud platforms
• Ensure reliability, evaluation, and performance of AI systems
What We’re Looking For:
• 7–12 years of experience in software engineering or AI/ML engineering
• Strong coding skills in Python
• Experience building production-grade backend systems (APIs, microservices)
• Hands-on experience with LLMs and GenAI applications
Must-Have Experience:
• Building agent-based AI systems (multi-agent workflows, orchestration, tool calling)
• Frameworks like LangGraph, LangChain, AutoGen, CrewAI (or similar)
• Developing and deploying RAG pipelines
• Working with FastAPI/Flask, microservices, distributed systems
• Experience with cloud (AWS/GCP/Azure), Docker, Kubernetes
Nice to Have:
• LLM evaluation tools (Ragas, Langfuse, etc.)
• Experience building production AI systems at scale
• Exposure to enterprise or financial systems
Not a Fit If:
• You’re primarily an architect, manager, or strategist
• Limited hands-on coding or system development
• Experience is limited to POCs or basic chatbot work
This role is ideal for engineers who build real AI systems end-to-end — from backend services to deployed agent workflows.