AI Engineer

About the Role 

You’ll develop Python backend services that power LLM-based applications, including RAG systems and agentic workflows. You’ll work closely with data engineers, ML engineers, and product teams to bring AI features from prototype to production. 

Key Responsibilities

• Build and maintain Python backend services for AI applications 

•  Implement RAG pipelines using vector databases and embedding models 

•  Integrate LLMs (OpenAI, Anthropic, open-source models) into production workflows 

•  Design and develop agentic workflows for multi-step reasoning tasks 

•  Optimize retrieval quality, latency, and cost across AI systems 

Required Qualifications

•  ~5 years of backend development experience, with strong Python skills 

•  Working knowledge of RAG architectures and retrieval pipelines 

•  Hands-on experience with vector databases (Pinecone, Weaviate, Qdrant, pgvector, or similar) 

•  Solid understanding of LLM integration fundamentals (prompting, embeddings, function calling) 

•  Familiarity with agentic workflows and frameworks like LangChain, LlamaIndex, or LangGraph 

•  Experience building and deploying REST/gRPC APIs 

Preferred Qualifications

•  Experience with model fine-tuning or evaluation pipelines 

•  Familiarity with cloud platforms (GCP, AWS, or Azure) 

•  Background in MLOps or LLMOps tooling.