EY - GDS Consulting - AIA - AI Data Engineer- Senior
Explicitly mentions "Vibe Coding" as a skill to leverage for building full‑stack applications, so it expects vibe coding experience.
About the Role
Senior AI Data Engineer role at EY GDS focused on designing and delivering production-grade GenAI and agentic AI data pipelines. The position leads development of LLM-based applications, RAG pipelines, multi-agent systems and cloud-native MLOps to drive AI strategy and enterprise implementations.
Job Description
Role
Senior AI Data Engineer on EY’s AIA (Artificial Intelligence & Automation) / Digital Engineering team responsible for designing, developing and deploying GenAI and agentic AI solutions. The role combines hands-on implementation of LLM-based applications, RAG pipelines and multi-agent orchestration with leadership responsibilities across strategy, proofs-of-concept and production rollouts.
Key Responsibilities
- Lead design, development and deployment of GenAI and Agentic AI solutions, including LLM-based applications, multi-agent systems, and RAG pipelines.
- Architect production-grade applications using LLMs (prompting, fine-tuning, evaluation) and build API/integration layers to connect AI capabilities with enterprise systems.
- Design and implement retrieval and knowledge solutions using vector databases, knowledge graphs and hybrid retrieval strategies.
- Build data pipelines and engineering workflows using Databricks, Spark, Airflow and Kafka; work with large-scale structured and unstructured datasets.
- Implement MLOps practices (CI/CD for ML, containerization, model versioning, reproducibility) and deploy/manage AI workloads on cloud platforms.
- Add observability and guardrails: monitor latency, model drift, token usage, performance metrics and responsible AI controls.
- Mentor and lead team members, conduct design discussions and code reviews, and present solutions to technical and business stakeholders.
Requirements
- 4+ years of hands-on experience designing and delivering enterprise AI solutions; 4–6 years data engineering experience expected.
- Strong proficiency in Python and SQL; experience with PyTorch, TensorFlow and Hugging Face Transformers.
- Hands-on experience with Databricks, Snowflake or Microsoft Fabric; distributed data processing knowledge (Spark).
- Experience building pipelines using Airflow and messaging/streaming systems such as Kafka.
- Familiarity with LLMs (GPT, Claude, LLaMA, Gemini), RAG patterns, vector databases, knowledge graphs and multi-agent frameworks.
- Experience with containerization and orchestration (Docker, Kubernetes) and MLOps tooling and practices.
- Experience deploying models on cloud platforms (Azure, AWS, GCP) and using managed AI services (Azure OpenAI, Azure AI Search, SageMaker, Vertex AI).
- Strong analytical thinking, structured problem solving and clear technical communication; ability to lead delivery under tight timelines.
Preferred / Good to Have
- Certifications in Azure AI (preferred), AWS Machine Learning or GCP Professional ML Engineer.
- Certifications or experience in MLOps, Kubernetes or DevOps for AI.
- Published research, patents or conference presentations in AI/ML or NLP.
Location & Team
- Primary location: Kolkata; role also listed as available “Anywhere in Country” (India). Part of EY Global Delivery Services (GDS) collaborating across multiple countries and service lines.
What EY Offers
- Emphasis on continuous learning, coaching and leadership development, global collaboration and a diverse, inclusive culture focused on career growth.