AI Engineer

We're looking for an AI Engineer who can build real-world LLM and retrieval-based features. You'll work across embeddings, chunking, vector search, evaluation, and reliability. This is a high-impact role with room to experiment and shape core AI foundations.

Responsibilities

• Build and optimize RAG pipelines (chunking, indexing, embeddings)

• Improve LLM accuracy, consistency, and response quality

• Experiment with model configurations and retrieval strategies

• Develop evaluation frameworks for LLM output quality

• Process large and complex documents with structured output generation

• Work with engineering to integrate AI features into production systems

• Diagnose LLM behaviour, troubleshoot retrieval issues, and improve reliability

Requirements

• 3-5+ years in AI/ML, NLP, or LLM engineering

• Strong Python development skills

• Experience with vector databases (Milvus, Pinecone, pgvector, MongoDB Atlas Search, etc.)

• Knowledge of embeddings, tokenization, and chunking techniques

• Experience with RAG pipelines or similar retrieval setups

• Familiar with LLM prompting, model tuning, or system behaviour evaluation

• Comfortable collaborating with backend/frontend engineering teams

• Experience building FastAPI or microservices

• Experience running experiments at scale or using evaluation frameworks

• Familiarity with agentic flows or tool-calling models