AI Engineer

Brak informacji o wynagrodzeniu

Nieokreślone0Full-time

#474996·Dodano 10 dni temu·4

Źródło: Xebia

Aplikuj teraz

Tech Stack / Keywords

LLMMCPOCRDocument AIembeddingsvector searchlexical searchknowledge graphA/B testing

Podsumowanie oferty

Build AI agents and related capabilities for credit, KYC/compliance, document handling and exception triage. The work includes LLM/agent workflows, MCP tool interfaces, Document AI and retrieval and evaluation capabilities for client solutions.

Wymagania

Hands-on experience building AI or agent-based solutions.
Experience designing or implementing LLM/AI agent workflows.
Experience with model integration and routing, including consideration of cost, latency and risk.
Experience designing controlled tool interfaces for AI agents.
Knowledge of MCP-based tool interfaces or comparable permissioned agent-tool integration approaches.
Practical experience with Document AI capabilities such as OCR, structured extraction, PII detection or masking.
Experience with retrieval architectures using embeddings and vector or lexical search.
Experience designing evaluation approaches for AI systems, including model or prompt evaluation.
Understanding of observability requirements for agent behaviour.
Ability to design AI solutions that operate through permissioned, logged and auditable interfaces.
Ability to collaborate across prototype and production-oriented engineering streams.

Nice to have:

Experience with self-hosted models in environments with data residency constraints.
Experience with knowledge graphs as contextual sources for AI agents.
Experience with multi-agent or multi-role decision patterns.
Experience with AI applications supporting credit, KYC, compliance, document processing or exception management.
Familiarity with deterministic core banking systems.
Experience with A/B testing of models or prompts.
Experience working in financial services, leasing or vendor finance.

Obowiązki

Build agents supporting credit, KYC/compliance, document handling and exception triage.
Implement multi-role decision patterns for high-impact cases, including analyst, critic and guardian roles.
Develop a model gateway to route requests between models according to cost, risk and latency.
Support self-hosted models where data residency requirements make this necessary.
Build MCP tool interfaces that restrict agent actions to permissioned and logged tools.
Develop Document AI capabilities covering OCR, information extraction, PII detection and masking.
Build retrieval and context capabilities using embeddings, vector search, lexical search and a knowledge graph.
Develop an evaluation framework for AI behaviour, including evals, A/B testing of models and prompts, and observability.
Work with the Foundation and Lab streams to ensure AI concepts can be implemented on the target platform.

Inne informacje

Work from the European Union region and a work permit are required.
The candidate must be ready to join within 2 weeks.
Recruitment process: CV review, HR call, interview, client interview, decision.

Xebia sp. z o.o.

124 aktywne oferty

Zobacz wszystkie oferty

Aplikuj teraz