Senior AI Engineer - Agentic AI
⚲ Copenhagen
Do uzgodnienia
Wymagania
- C#
- Python
- Banking Systems
- Artificial Intelligence (AI)
- Financial Services
- Microsoft Platform
- Amazon Web Services (AWS)
- Prompt Engineering
Opis stanowiska
On behalf of a client in the financial sector, we are looking for a Senior AI Engineer. The consultant will help develop and implement AI agents and agentic workflows aimed at improving productivity and automating analytical tasks. This is a hands-on role focused on applying modern AI technologies to solve real business challenges and create value for end users.
Main Responsibilities:
• Design and implement AI agents to improve banker productivity
• Build multi-agent workflows utilizing AWS Bedrock and Agent Core
• Engineer memory systems and RAG pipelines connecting to internal and external data sources
• Create multi-agent orchestration patterns for efficient task management
• Develop prompt engineering strategies and evaluation frameworks for consistent outputs
• Write robust, production-grade Python/C# code with complete test coverage
• Collaborate with Domain SMEs for task decomposition and evaluation rubrics
• Maintain agent evaluation frameworks to monitor quality and performance
Key Requirements:
• 5+ years software engineering, 2+ years focused on LLM/AI systems
• Hands-on AWS Bedrock and at least one orchestration framework (LangChain, LangGraph, or similar)
• Production Python/C# experience building and shipping AI systems
• Strong understanding of memory and RAG architectures, vector databases, and embedding models
• Experience with tool-use / function-calling patterns in LLM applications IT Consultancy Request
• Familiarity with LLM evaluation frameworks (relevance, faithfulness, hallucination detection)
Nice to Have:
• Hands-on AWS Agent Core experience
• Financial services background banking workflows, credit analysis, or capital markets
• Fine-tuning or RLHF experience on domain-specific models
• Familiarity with LSEG, Bloomberg, or financial data APIs as an integrator
Other Details:
• Work Location: Copenhagen, Denmark (Hybrid)
• Allocation: Full-time
• Assignment Start Date/End Date: ASAP until 31.12.2026, with potential for extension
Main Responsibilities:
• Design and implement AI agents to improve banker productivity
• Build multi-agent workflows utilizing AWS Bedrock and Agent Core
• Engineer memory systems and RAG pipelines connecting to internal and external data sources
• Create multi-agent orchestration patterns for efficient task management
• Develop prompt engineering strategies and evaluation frameworks for consistent outputs
• Write robust, production-grade Python/C# code with complete test coverage
• Collaborate with Domain SMEs for task decomposition and evaluation rubrics
• Maintain agent evaluation frameworks to monitor quality and performance
Key Requirements:
• 5+ years software engineering, 2+ years focused on LLM/AI systems
• Hands-on AWS Bedrock and at least one orchestration framework (LangChain, LangGraph, or similar)
• Production Python/C# experience building and shipping AI systems
• Strong understanding of memory and RAG architectures, vector databases, and embedding models
• Experience with tool-use / function-calling patterns in LLM applications IT Consultancy Request
• Familiarity with LLM evaluation frameworks (relevance, faithfulness, hallucination detection)
Nice to Have:
• Hands-on AWS Agent Core experience
• Financial services background banking workflows, credit analysis, or capital markets
• Fine-tuning or RLHF experience on domain-specific models
• Familiarity with LSEG, Bloomberg, or financial data APIs as an integrator
Other Details:
• Work Location: Copenhagen, Denmark (Hybrid)
• Allocation: Full-time
• Assignment Start Date/End Date: ASAP until 31.12.2026, with potential for extension
🔍 Dekoder Ogłoszenia
🔴
hands-on role focused on applying modern AI technologies to solve real business challenges and create value for end users
Oczekuje się, że będziesz samodzielnie implementować rozwiązania, a nie tylko nadzorować.
🟡
improve banker productivity
Może oznaczać automatyzację prostych, powtarzalnych zadań, które niekoniecznie są ekscytujące.
🟡
production-grade Python/C# code with complete test coverage
Oznacza to, że kod musi być wysokiej jakości i dobrze przetestowany, co może pochłaniać dużo czasu.
🟡
Collaborate with Domain SMEs for task decomposition and evaluation rubrics
Będziesz musiał dużo rozmawiać z ekspertami dziedzinowymi, aby zrozumieć ich potrzeby i zdefiniować cele.
🟡
Maintain agent evaluation frameworks to monitor quality and performance
Część pracy będzie polegać na monitorowaniu i ulepszaniu istniejących systemów, a nie tylko na tworzeniu nowych.