Applied AI Engineer
ExpiredThis listing is older than 60 days and may no longer be accepting applications.
This listing is older than 60 days and has likely been filled. Here are open roles like it:
Samsara
Influur
Benchling
Get new agentic engineering jobs in your inbox every Monday.
One curated email a week. No spam, unsubscribe anytime.
Tech Stack
About the Role
Pager Health seeks a builder to develop production-grade LLM-powered agent systems. This is a hands-on engineering role focused on translating specifications into robust, deployable services rather than research work. You will handle the complete lifecycle from prototyping through production deployment.
Responsibilities
- Build agentic applications and workflows using LLM frameworks and guardrails
- Implement tool integrations and orchestration logic across internal and external APIs
- Deploy RAG pipelines with vector store integration and optimization
- Own full lifecycle from prototype through production monitoring
- Build evaluation infrastructure to measure agent quality, latency, and safety
- Collaborate with data science and infrastructure teams
- Deploy services across GCP/Vertex AI, AWS Bedrock, and Azure OpenAI
Requirements
- 3+ years software engineering with Python proficiency
- Hands-on LLM application development (Claude, GPT, Gemini)
- Agent framework experience (LangChain, LangGraph, CrewAI, or similar)
- RAG architecture and vector database knowledge (Pinecone, Weaviate, pgvector)
- Cloud deployment experience (GCP/Vertex AI, AWS Bedrock, Azure)
- Function calling and multi-step workflow implementation
- API design and microservices deployment
Nice-to-have: MLOps, CI/CD, evaluation frameworks (RAGAS, LangSmith), GCP/Vertex AI expertise.
Compensation: $150,000 - $160,000 plus equity and benefits (for CO, NV, NY, DC).