AI Engineer

About the role

A role building the language and language model systems behind an AI platform for customer service. The engineer will shape pipelines from classic text processing through retrieval and agentic workflows.

What you will do

• Build end to end NLP pipelines, from classic text processing to LLM driven designs
• Create intent detection, named entity recognition and text classification components
• Design retrieval augmented generation systems, including chunking, vector stores and re-ranking
• Implement agentic patterns such as tool use, function calling and multi step reasoning
• Set up memory and context handling for multi turn conversations
• Benchmark models for hallucination, faithfulness, latency and token cost, then ship them as low latency services

What they look for

• One to three years in data science, AI or NLP engineering
• Strong Python plus libraries such as Pandas, scikit-learn, NLTK, spaCy and Gensim
• Grasp of NLP basics including embeddings, NER, extraction, intent and similarity
• Experience putting machine learning products into production
• Hands on work with large language models in production
• Familiarity with retrieval pipelines and vector databases

Nice to have

• Agentic frameworks, function calling or structured outputs
• Voice AI or speech to text exposure
• Cloud infrastructure and ML deployment on AWS, GCP or Azure

Benefits

• Competitive compensation package
• Health insurance
• Career growth opportunities
• Training, events and conferences
• Remote first model with office perks