AI/ML Engineer

We are looking for an AI/ML Engineer to build a production-grade document intelligence and query system using advanced RAG (Retrieval-Augmented Generation) or RLM (Recursive Language Model) approaches.

Responsibilities:

• Design and implement advanced RAG pipelines using frameworks like LangChain (or equivalent)
• Develop and experiment with RLM (Recursive Language Models) or recursive agent-based architectures
• Build a document/query system capable of handling enterprise data sources (CSV, ERP exports, SAP, Shopify, etc.)
• Perform comparative analysis between traditional RAG and RLM approaches (accuracy, latency, cost, reliability)
• Work with local LLMs (Ollama) for on-prem or controlled deployments
• Implement data ingestion, chunking, embedding, and retrieval strategies
• Develop clean, modular backend services (APIs, pipelines) for the solution
• Optimize system performance, including response quality, latency, and resource usage
• Document architecture decisions, trade-offs, and evaluation results

Qualifications:

• Proven experience building production-grade RAG pipelines (LangChain or similar frameworks)
• OR hands-on experience with RLM (Recursive Language Models) or recursive/agentic AI systems
• Strong experience working with enterprise datasets (CSV files, ERP systems, SAP, Shopify, etc.)
• Experience using local LLMs (e.g., Ollama) for deployment and inference
• Proficiency in Python and backend development (FastAPI, Flask, or similar)
• Solid understanding of:
• Embeddings and vector databases
• Semantic search and retrieval techniques
• Prompt engineering and LLM behavior