Role Summary:

Build and run our AI services for document understanding, RAG and policy extraction to support HR and payroll decisions. 

Key Responsibilities 

• Build data pipelines to ingest laws, HR policies and company documents. 

• Design and run RAG pipelines using LLMs and vector databases. 

• Create prompts and tools to extract structured rules from text. 

• Work with backend engineers to connect AI outputs to rule engines and APIs. 

• Evaluate AI quality, improve prompts and retrieval, and track key metrics. 

• Document your work clearly and share best practices with the team. 
  

Requirements (Must Have) 

• 4+ years of experience in ML / AI software development. 

• Strong Python skills. 

• Hands-on experience with LLM APIs (such as OpenAI) and embeddings. 

• Experience with at least one vector database (Pinecone, Qdrant, Weaviate, etc.). 

• Experience with at least one RAG or LLM orchestration framework (LangChain, LlamaIndex or similar). 

• Experience building and deploying ML/AI services in production. 

• Strong understanding of evaluation and monitoring for AI systems. 
  

Good to Have 

• Background in NLP or information retrieval. 

• Experience with legal tech, HR tech or regulatory technology. 

• Experience with human-in-the-loop workflows and confidence-based routing. 

• Experience with rule engines or policy-as-code frameworks.