Senior AI Lead Architect: RAG, LLMs & Python

Synechron; Charlotte (NC); On-site; USD 120,000 - 140,000; Full time

Benefits offered by this job

Competitive package

Work abroad opportunities

Paid annual leave

Maternity & paternity leave

Insurance plan (medical, dental,Vision

Life insurance

Disability coverage

Retirement savings plans

Udemy for Business access

Training opportunities

Job summary

Synechron is seeking a hands-on AI Lead Architect to design and deliver scalable Generative AI solutions, including end-to-end RAG pipelines and production-grade Python APIs. You will work with LLMs, embeddings, and vector databases, deploying on AWS/Azure/Google Cloud, with strong focus on governance, security, and LLMOps.

The role requires 3+ years delivering AI solutions, experience building RAG apps, and familiarity with LangChain/LlamaIndex.

Qualifications

• 3+ years hands-on experience delivering AI or Generative AI solutions.
• Proven experience building and deploying RAG applications.
• Knowledge of LLMs, embeddings, semantic search, vector databases, APIs, and cloud architecture.
• Experience with frameworks such as LangChain, LlamaIndex, Semantic Kernel, or similar.
• Familiarity with Docker, Kubernetes, CI/CD, databases, security, and automated testing.

Responsibilities

• Lead the architecture and delivery of enterprise AI and Generative AI solutions.
• Design and implement RAG pipelines (ingestion, chunking, embeddings, retrieval, reranking, response generation).
• Develop production-grade Python applications, APIs, and AI workflows.
• Work with LLMs, prompt engineering, AI agents, tool calling, and model evaluation.
• Use cloud platforms such as AWS, Azure, or Google Cloud.
• Implement Docker, Kubernetes, CI/CD, MLOps, and LLMOps practices.
• Ensure AI solutions are secure, compliant, observable, scalable, and cost-effective.
• Lead technical discussions and mentor engineering teams.

Skills

Generative AI

RAG pipelines

Python

LLMs

Cloud platforms

Docker/Kubernetes

LLMOps

Tools

LangChain

LlamaIndex

Semantic Kernel

Docker

Kubernetes

Job description

Synechron is seeking a hands-on AI Lead Architect to design and deliver scalable Generative AI solutions, including end-to-end RAG pipelines and production-grade Python APIs. You will work with LLMs, embeddings, and vector databases, deploying on AWS/Azure/Google Cloud, with strong focus on governance, security, and LLMOps.

The role requires 3+ years delivering AI solutions, experience building RAG apps, and familiarity with LangChain/LlamaIndex.