Who we'd reach at Syren CloudFound and reached by Power Apply
Best leadEngineering manager
Leads the team you would join
Technical recruiter
Owns the opening
Team member
On the team, can refer you
From your own Gmail and LinkedIn.
About the role
This is a full-time senior or lead AI engineer role focused on generative AI, RAG and agentic AI applications for enterprise use, and the posting expects five or more years of experience. It suits a hands-on Python engineer who has built LLM applications and can take them to production, including with LangChain or LangGraph, and the location is not stated. The work covers conversational assistants, retrieval pipelines and multi-agent workflows that connect to business systems.
What you’ll do
- Design and deploy LLM-based applications such as conversational assistants and copilots.
- Build document ingestion, indexing, embedding and retrieval pipelines.
- Connect knowledge sources including databases, SharePoint, APIs, documents and cloud storage.
- Tune chunking, retrieval, reranking and grounding to improve answer quality.
- Build multi-agent workflows that plan, reason, use tools and complete tasks, with memory and orchestration.
- Integrate agents with enterprise applications and business processes.
- Build FastAPI services and REST APIs, with logging, monitoring and error handling.
- Deploy to Azure, AWS or GCP with CI/CD, attention to security, cost and performance.
- Evaluate model responses and add guardrails for responsible use.
What they’re looking for
- Five or more years of experience.
- Strong Python development skills.
- Hands-on experience with LangChain and LangGraph, and familiarity with CrewAI or AutoGen.
- Experience designing RAG architectures and LLM applications.
- Experience with FastAPI and REST APIs.
- Cloud deployment experience on Azure, AWS or GCP.
Skills
Questions about this role
How much experience is required?
Five or more years.
Is the role full-time?
Yes.
Which agent frameworks are named?
LangChain, LangGraph, CrewAI and AutoGen.