Senior AI & Vector RAG Systems Engineer
Senior AI & Vector RAG Systems Engineer Role Overview
Join our AI Engineering team to build enterprise Python RAG vector pipelines, LLM agent orchestrations, and document processing automation for InsurTech and FinTech clients.
Key Responsibilities: Senior AI & Vector RAG Systems Engineer
- ✓ Build vector embedding pipelines using Pinecone, Qdrant, and OpenAI models
- ✓ Implement LangChain and LlamaIndex retrieval frameworks for unstructured PDF claims parsing
- ✓ Integrate Python AI microservices with Laravel and Node.js backends
- ✓ Optimize vector search precision and reduce model API token latency
Technical Requirements & Qualifications
- ⚡ 4+ years building production AI microservices with Python, FastAPI, and PyTorch/TensorFlow
- ⚡ Demonstrated expertise with Pinecone, Chroma, or Qdrant vector databases
- ⚡ Solid knowledge of prompt engineering, fine-tuning, and RAG evaluation metrics
- ⚡ Experience deploying containerized microservices on AWS / GCP
Apply For This Position
Complete the form below to submit your application directly to our engineering hiring team.
Frequently Asked Questions About This Position
What primary AI architectures and toolchains will this engineer build?
You will engineer production retrieval-augmented generation (RAG) pipelines, semantic chunking pipelines, vector indexing with pgvector and specialized vector databases, fine-tune open-weights models, and build hallucination mitigation guardrails.
What foundational experience is required for this senior AI role?
We seek engineers with 5+ years of software engineering experience, including 2+ years of production experience implementing vector search, embedding models, Python asynchronous frameworks, and enterprise document ingestion.
How does Nexura ensure ethical AI practices and data privacy in client solutions?
We enforce strict zero-data-retention policies, on-premise/VPC deployments, and automated PII redaction layers, ensuring client intellectual property is never used for external model training.
What is the expected timeline for hiring and onboarding?
We complete technical assessments within 7 to 10 business days of initial application review, with immediate onboarding into ongoing enterprise AI engineering sprints.