AI Engineer: NLP & LLMs

Company Description

Zyphe provides a privacy-first identity verification solution that prioritizes user control over personal data while ensuring businesses are protected from fraud and data breaches. Powered by a decentralized platform, Zyphe enables seamless identity verification and retention without storing Personally Identifiable Information (PII) on company servers. With advanced KYC, AML, and KYB modules built on Web3 principles, Zyphe helps organizations meet modern privacy and security requirements. The platform also offers users secure identity vaults and effortless one-click verification for smooth onboarding experiences.

Role Overview

We're looking for an AI Engineer specializing in NLP and Large Language Models to build intelligent language systems that power our compliance automation and document understanding capabilities.

This is not a prompt-engineering role. You will own the full NLP stack, from fine-tuning foundation models to designing production RAG pipelines and evaluation frameworks.

You'll work at the intersection of LLM engineering, information extraction, and regulatory intelligence, building systems that understand complex compliance documents and automate decision-making.

What You'll Do

• Build and fine-tune large language models for document classification, entity extraction, and compliance analysis
• Design and optimize Retrieval-Augmented Generation (RAG) pipelines for regulatory knowledge bases
• Develop prompt engineering frameworks and evaluation harnesses for LLM-powered features
• Implement inference optimization strategies (quantization, distillation, speculative decoding)
• Build structured output extraction from unstructured identity documents and compliance filings
• Create automated evaluation pipelines to measure accuracy, hallucination rates, and latency
• Collaborate with product and compliance teams to translate regulatory requirements into AI capabilities
• Stay current with the fast-moving LLM landscape and evaluate new models and techniques

What We're Looking For

• Strong experience building production NLP systems, not just prototypes
• Deep understanding of transformer architectures, attention mechanisms, and training dynamics
• Hands-on experience with LLM fine-tuning (LoRA, QLoRA, full fine-tuning) and RLHF/DPO
• Proven ability to design and optimize RAG systems at scale
• Experience with inference optimization and model serving (vLLM, TGI, or similar)
• Strong Python skills and familiarity with the HuggingFace ecosystem
• Understanding of evaluation methodologies for generative AI systems
• Experience with information extraction from semi-structured documents is a plus

What Makes You a Great Fit

• You think in systems, not models, you care about the full pipeline from retrieval to generation
• You're obsessed with measurable quality, hallucination rates, precision, and user impact
• You combine deep ML knowledge with pragmatic engineering
• You don't just follow trends, you evaluate critically and ship what works