Agentic AI Engineer

Jelentkezés a cégnél

Cég neve

Accenture Korlátolt Felelősségű Társaság
Munkavégzés helye

Budapest

Munkaidő, foglalkoztatás jellege
- Alkalmazotti jogviszony
- Általános munkarend
Elvárt technológiák
- PYTHON DEBUGGING TESTING TROUBLESHOOTING REGRESSION TESTING
Elvárások
- Angol középfok
- 1-3 év tapasztalat
- Középiskola

Állás elmentve

A hirdetést eltávolítottuk a mentett állásai közül.

Responsibilities

Design and implement agent-to-agent communication patterns and multi-agent collaboration workflows
Integrate LLMs, RAG pipelines, and external APIs/tools into end-to-end agent systems
Develop, test, and iterate on orchestration logic including routing, planning, tool selection, error handling, and structured execution
Build prompt templates, memory/state management, and reusable workflow components to improve reliability and consistency
Implement and optimize RAG and embedding workflows including retrieval strategy, chunking, evaluation, and iteration
Own testing and debugging for multi-agent systems including tracing, evaluation, and regression testing across workflows

Requirements

Hands-on experience building LLM-based applications in Python including structured prompting and multi-step workflows
Practical experience with at least one agent framework or orchestration approach such as LangChain or a comparable framework
Working knowledge of prompt templates and basic memory/state concepts such as session memory, conversation state, lightweight persistence
RAG fundamentals with implementation exposure including building a basic retrieval flow from data to grounded answer and iterating on quality
Debugging mindset for agentic workflows including troubleshooting tool-calls, retrieval misses, and prompt/chain issues and familiarity with logs, traces, or basic observability practices
Strong English language knowledge

Nice-to-have

Experience with LangGraph for graph/state-machine orchestration, Experience with multi-agent patterns, Experience with Langfuse or similar tracing and evaluation tooling for prompt/version tracking, traces, and quality monitoring, Experience improving RAG quality beyond basics including evaluation, retrieval strategies, and chunking experiments, Exposure to testing practices for LLM applications including lightweight evaluation, regression checks, and reproducibility habits

Company info

Accenture is a company where more than 775,000 employees help stakeholders continuously reinvent. The company drives positive change and delivers value to clients, partners, shareholders, communities, and each other. Accenture fosters an inclusive and diverse environment free from bias, supporting employees' physical, mental, and financial health. The company provides opportunities for skill development through certifications, learning, and diverse work experiences and is recognized as one of the World's Best Workplaces™.