Senior Applied AI Engineer — Remote, RAG & LLM Delivery

N-iX; Kraków; Hybrid; PLN 180,000 - 270,000; Full time

Benefits offered by this job

Flexible work format

Education reimbursement

Mentorship program

Tech talks

Corporate events

Team building

Centers of excellence

Job summary

N-iX is seeking a Senior Applied AI Engineer to design, build and ship customer-facing AI features end-to-end for a fast-growing fintech client.

You will own RAG system design (chunking, embedding selection, retrieval, re-ranking) and agentic workflows, ensuring safe production deployment and robust observability. The role requires hands-on experience shipping external LLM-based features and strong data fluency.

Qualifications

• Proven experience shipping external customer-facing LLM-based features to production.
• Hands-on evaluation-pipeline and observability work: drift detection and quality monitoring.
• Strong data fluency to reason about retrieval architecture.

Responsibilities

• Design, build and ship customer-facing AI features end-to-end, including RAG system design and agentic workflows.
• Ship external customer-facing LLM-based features into production with safe deployment practices.
• Perform hands-on evaluation, drift detection and quality monitoring in production pipelines.
• Reason independently about retrieval architecture using data fluency.
• Develop and observe the Context Development Lifecycle for AI agents.
• Share patterns and practices to enable broader adoption across the organisation.
• Embed directly into a client squad as a hands-on Individual Contributor.

Skills

Python

RAG system design

Agentic workflows

Production deployment

Evaluation-pipeline

Data fluency

Guardrails & verification

Claude Code & Copilot

Tools

AWS Bedrock

OpenAI APIs

Langfuse

Job description

N-iX is seeking a Senior Applied AI Engineer to design, build and ship customer-facing AI features end-to-end for a fast-growing fintech client.

You will own RAG system design (chunking, embedding selection, retrieval, re-ranking) and agentic workflows, ensuring safe production deployment and robust observability. The role requires hands-on experience shipping external LLM-based features and strong data fluency.