Gen AI Lead Developer - Senior Consultant

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. 

Job Title: Gen AI Full Stack Engineer (Senior Consultant)

Department: Generative AI

Role Overview:

We are seeking a Senior GenAI Engineer who will lead the development of intelligent, data-driven applications with Generative AI as a core design element. In this consulting role, you will design, develop, and deploy scalable, production-ready software across the stack (backend, frontend, APIs, and data layers) that incorporate large language models (LLMs) and AI-driven features from the ground up. You will work closely with cross-functional teams and clients to deliver business-impactful AI solutions, ensuring robust engineering practices, cloud-native architecture, and a focus on automation and AI-assisted workflows. This position emphasizes software engineering excellence combined with hands-on AI/ML expertise to create innovative solutions (such as LLM-based assistants, RAG pipelines, and multi-agent systems) that enhance user experiences and optimize business processes.

Responsibilities:

• AI-Driven Application Design: Embed AI/ML components (e.g., NLP, LLMs, recommender systems) as a core part of system architecture to improve automation, decision support, and user experience — not as an afterthought. Innovate by applying AI-assisted workflows to solve complex problems in domains like finance, energy, supply chain, etc., driving measurable business outcomes.
• Generative AI & Agentic Workflows: Design and implement GenAI features and intelligent agent workflows using state-of-the-art LLMs (e.g., GPT, Claude, Llama, Mistral or similar). Build Retrieval-Augmented Generation (RAG) pipelines (involving data indexing, chunking, vector embeddings, and retrieval/reranking mechanisms) to ground LLM outputs in enterprise data. Develop advanced multi-agent systems and automated AI processes, ensuring robust prompt management, tool usage, and flow orchestration (with safeguards like caching, retries, and cost controls).
• Full-Stack Development: Independently design, build, test, and maintain high-quality software solutions, spanning backend services (using modern frameworks and languages such as . net, .net core, python ) and front-end applications (with React or Angular) , while integrating AI capabilities at every layer.
• Cloud-Native AI Solutions: Deploy and operate AI solutions on cloud platforms (AWS, Azure, or similar) using modern DevOps and MLOps practices. Implement containerization (Docker, Kubernetes), CI/CD pipelines, and monitoring/observability for production AI services. Ensure that LLM solutions are secure, scalable, and cost-effective, with clear logging and telemetry for model performance and user interactions.
• Collaborative Delivery: Work closely with clients and multidisciplinary teams (developers, data scientists, architects, product managers) to translate business requirements into technical solut i ons . Guide project decisions with a consulting mindset, ensuring alignment of AI solutions with client goals and compliance requirements. Provide support for deployments and iterative improvements post-launch, including training client teams and addressing production issues.
• Continuous Improvement: Keep up to date with emerging AI technologies and frameworks (e.g., LangChain/LangGraph, Semantic Kernel, AutoGen, etc.) and AI-assisted development tools (like GitHub Copilot). Champion best practices in software engineering and AI integration, and proactively introduce improvements to enhance developer productivity, system reliability, and AI result quality.

Essential Qualifications:

• Bachelor’s degree in Computer Science, Software Engineering or related field (or equivalent practical experience).
• 5+ years of professional software engineering experience with a focus on full-stack development and AI/ML integration.
• Proven track record in delivering AI-powered solutions (especially generative AI or machine learning projects) that achieved tangible business impact.
• Strong problem-solving skills and the ability to independently design, debug, and optimize complex systems.
• Excellent communication and collaboration skills, with experience working in cross-functional and client-facing environments.
• Willingness and ability to travel up to 25% (as needed) for client engagements or collaborative on-site work.

Must have Skills:

• Backend Development: Proficiency in at least one modern backend language (e.g., Python, Java, C#, or JavaScript/TypeScript ) and its frameworks (such as Node.js, .NET Core) for building scalable server-side applications and RESTful APIs.
• Frontend Development: Hands-on experience with modern frontend frameworks (e.g., React, Angular ) to create responsive, user-friendly interfaces. Ability to integrate UI components with backend AI services.
• Databases: Strong skills in working with both relational (SQL) and non-relational (NoSQL) databases, including schema design, query optimization, and data modeling for large-scale applications.
• AI & LLM Expertise: Proven experience building and deploying LLM-based solutions – e.g., developing chatbot/assistant applications, implementing RAG pipelines (text chunking, embeddings generation, retrieval, reranking), and working with large language model APIs or frameworks. Familiarity with transformer models and concepts like prompt engineering, LLM fine-tuning, and multi-agent AI patterns.
• Cloud & DevOps: Experience building cloud-native applications and using DevOps practices – including CI/CD pipelines, Git-based version control, infrastructure-as-code, and automated testing. Hands-on experience with containerization and orchestration tools like Docker and Kubernetes, and familiarity with cloud services for compute, data storage, identity, and monitoring.
• Software Engineering Fundamentals: Strong foundation in computer science and software engineering principles (algorithms, data structures, design patterns). Ability to apply modern design approaches (e.g., distributed systems, event-driven architecture) while incorporating AI capabilities early in the design process .
• Quality & Security: Understanding of security, identity, and access management in cloud and AI systems. Familiarity with CI/CD, production observability, and support processes for maintaining high availability and reliability of enterprise applications.
• (Good to have ) : ML Platforms & Tools : Hands-on experience with at least one modern cloud-based AI/ML platform such as Databricks ( MLflow, AutoML ), Azure Machine Learning, or Snowflake (Snowpark ML, Cortex) . Proficiency with common machine learning libraries (e.g., scikit-learn, pandas, NumPy, XGBoost, LightGBM ) and deep learning frameworks (TensorFlow, PyTorch).

This Full-Stack Gen AI Engineer (Senior Consultant) role is ideal for a seasoned developer who combines deep software engineering expertise with cutting-edge AI/ML knowledge. If you are passionate about building innovative AI-driven systems, comfortable working across the full technology stack, and eager to help organizations harness the power of AI in their products and processes, we invite you to apply.

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.