EY Türkiye - Junior Applied AI Engineer

Descripción del puesto:

_________

At EY, we're all in to shape your future with confidence.

We'll help you succeed in a globally connected powerhouse of diverse teams and take your career wherever you want it to go.

Join EY and help to build a better working world.

The opportunity

EY is a global leader in Assurance, Consulting, SaT (Strategy &Transactions) and Tax services.

Enabled by data, AI and advanced technology, EY teams help clients shape the future with confidence and develop answers for the most pressing issues of today and tomorrow. The insights and quality services we provide help build trust and confidence in the capital markets and in economies the world over. Our offices around the world use the same methodology and are linked through an integrated technology platform to enable instantaneous communication and collaboration among team members, regardless of location. As a member of EY Global, in Türkiye we operate in 6 offices located in İstanbul, Ankara, Bursa, İzmir and Adana, with more than 1800 people for over 40 years.

At EY, we empower our 400.000 people in more than 150 countries with the right mindsets and skills to navigate what's next, become the transformative leaders the world needs, pursue careers as unique as they are, and build their own exceptional EY experiences. We work together across our full spectrum of services and skills so that business, people and the planet can thrive together.

Together, all in, to build a better working world.

As an Assistant, you will be a hands-on Python engineer on our delivery projects. We build production AI systems for real enterprise clients -decision-support engines, retrieval-augmented (RAG) pipelines, conversational agents with human-in-the-loop workflows. Our work is not research and not demos: what we ship gets used by finance teams, operations teams, and field users, which means data contracts, tests, scope limits, and auditability matter as much as model output. You will work directly with experienced engineers and architects, and you will touch real delivery from your first sprint. Our project portfolio is growing - this is a long-term engineering role, not a position tied to a single project's timeline.

Apply now if you are 4th year student graduating in June 2026 or if you have up to one year experience, and interested in an entry level position in our AI Services Team.

Your Key Responsibilities
* Build and extend LLM integration layers - prompt construction, structured outputs, evaluation harnesses, guardrails that keep the LLM in an "explain and summarize" role rather than an autonomous decision-maker.
* Work on retrieval pipelines - chunking and indexing domain documents, tuning retrieval quality, versioning knowledge bases.
* Write data preprocessing and validation code - file-based ingestion, schema validation with Pydantic, data-quality and anomaly checks.
* Implement rule + deviation logic - deterministic business rules (often YAML-defined) that the AI layer explains, not overrides.
* Write tests - unit, integration, and scope-limit regression tests. We treat "the system refuses to do what it shouldn't" as a feature with test coverage.
* Contribute to agentic workflows - bounded, tool-using flows with clear boundaries and human review points.

What We're Looking For
* Python (primary language - this is the core skill we hire for)
* FastAPI for service layers
* Azure OpenAI and the surrounding Azure family (Blob Storage, Entra ID, AI Search)
* Vector databases (Azure AI Search, Qdrant, or similar)
* Pydantic for data contracts, YAML for rule/config schemas
* pytest, GitHub Actions / Azure DevOps for CI
You do not need prior experience with all of these. You need solid Python and the ability to pick the rest up quickly.
Hard requirements:
* A bachelor's degree in computer science, engineering, or another quantitative field.
* Professional working English - our documentation, code review, and a good part of client-facing material is in English.
* Solid Python fundamentals: you can write clean functions and classes, handle errors deliberately, and explain what your code does and why.
Strongly valued (not required):
* You have built something - a team project at university, a solo side project, a thesis implementation, freelance work. If you have something to show, we will actually read it. A polished portfolio is not required; evidence of capability is what counts.
* Exposure to LLM APIs, RAG, or agent frameworks - even a small personal experiment counts if you can reason about what worked and what didn't.
* Experience working in a team: git workflow, code review, dividing work, disagreeing productively.
* Curiosity about why systems behave the way they do, not just how to make the error go away.

What You Can Expect
* Application
* Exam
* Interview Stages
* HR Interview
* Manager Interview
* Partner Interview
* Welcome!

Send your CV and include a link to your GitHub profile or any project you'd like us to look at. A short note (a few sentences, not a cover letter) on something you built and what you learned from it is more useful to us than a formal letter.

Are you ready to shape your future with confidence? Apply today.

To help create the best experience during the recruitment process, please describe any disability-related adjustments or accommodations you may need.

EY | Building a better working world

EY is building a better working world by creating new value for clients, people, society and the planet, while building trust in capital markets.

Enabled by data, AI and advanced technology, EY teams help clients shape the future with confidence and develop answers for the most pressing issues of today and tomorrow.

EY teams work across a full spectrum of services in assurance, consulting, tax, strategy and transactions. Fueled by sector insights, a globally connected, multi-disciplinary network and diverse ecosystem partners, EY teams can provide services in more than 150 countries and territories