EY - GDS Consulting - AIA - Gen AI - Senior

AI Developer (Python) Experience – 4-8 years’ experience

Skills and attributes for success

• Candidate must possess proficiency in the following technologies:
  • Core AI Engineering & LLM Frameworks :
    Python, LangChain, LangGraph, Auto Gen, Google Agent SDK, Model Context Protocol, Skills-based agent frameworks.
  • GenAI / Agentic AI Systems:
    LLM application development, agentic AI architectures, multi-agent workflows, prompt engineering, AI system design, tool/function calling, enterprise AI integration.
  • RAG, Embeddings & Vector Search:
    Retrieval-Augmented Generation pipelines, embeddings, semantic search, context retrieval strategies, Azure AI Search, Pinecone, FAISS, Redis Vector, pgvector.
  • Backend & API Engineering:
    Python, Fast API, REST API design, scalable API platforms, event-driven systems, microservices architecture, third-party system integration.
  • Cloud, Infrastructure & Containers:
    Azure OpenAI, Azure AI Services, Docker, Kubernetes, OpenShift, cloud-native application development, containerized deployments.
  • Databases & Data Platforms:
    SQL, NoSQL, MongoDB, Redis, ClickHouse, database design, performance optimization, data accuracy and integrity.
  • AI Model Engineering:
    Model fine-tuning, LoRA, BERT, LLM architecture understanding, evaluation techniques, AI performance monitoring.
  • AI Governance, Security & Responsible AI:
    PII protection, data privacy, AI security, compliance, responsible AI practices, governance controls, monitoring and observability frameworks.
  • DevOps & Engineering Practices:
    GitHub Actions, GitLab CI, CI/CD pipelines, source control, automated testing, production deployment practices, observability and monitoring.
  • Preferred Technologies:
    Rust, Go, Kubernetes, OpenShift, advanced vector database platforms, enterprise-scale LLM deployment patterns.

To qualify for the role, you must have

• Minimum of 4+ years of professional engineering experience, with hands-on experience in backend/platform engineering and GenAI/LLM systems.
• Bachelor’s degree B.E./B.Tech in Computer Science, IT, or related engineering discipline.
• Strong hands-on proficiency in Python for AI application development, backend services, and platform engineering.
• Demonstrable experience building LLM-powered applications, including RAG pipelines, agentic workflows, prompt engineering, and enterprise AI integrations.
• Hands-on expertise with LangChain and LangGraph, with exposure to frameworks such as AutoGen, Google Agent SDK, Model Context Protocol, or Skills-based agent frameworks.
• Experience designing and implementing Retrieval-Augmented Generation pipelines using vector databases such as Azure AI Search, Pinecone, FAISS, Redis Vector, or pgvector.
• Strong understanding of embeddings, semantic search, context retrieval strategies, chunking approaches, ranking, and retrieval optimization.
• Proficiency in building scalable backend services using Python, FastAPI, REST APIs, microservices, and event-driven architecture.
• Experience working with Azure OpenAI and Azure AI Services for enterprise-grade AI solution development.
• Strong understanding of Docker and containerized deployments, with exposure to Kubernetes or OpenShift preferred.
• Experience implementing CI/CD pipelines using GitHub Actions, GitLab CI, or similar DevOps tooling.
• Proficiency in SQL and NoSQL database design, query optimization, and scalable data interaction patterns.
• Familiarity with AI evaluation, observability, monitoring, and production support for LLM-based systems.
• Strong understanding of PII protection, data privacy, AI security, compliance, and responsible AI practices.
• Ability to collaborate with cross-functional teams, including AI engineers, data engineers, cloud/platform teams, security teams, product owners, and business stakeholders.
• Experience in banking or financial services domain is preferred, especially exposure to regulatory, security, and compliance requirements.
• Ability to troubleshoot and debug issues across AI pipelines, backend services, APIs, vector stores, cloud services, and production environments.
• Commitment to engineering quality, including maintainable code, automated testing, reusable components, documentation, and scalable design practices.

What we looking for

• Provides intermediate to senior-level system analysis, architecture design, development, and implementation of AI platforms, backend services, APIs, and enterprise AI systems.
• Designs and develops scalable GenAI applications using LLM frameworks, RAG pipelines, vector databases, and cloud-native backend services.
• Translates business and technical requirements into robust AI engineering solutions, including APIs, agentic workflows, retrieval pipelines, integrations, and data processing components.
• Builds, tests, and deploys AI-powered backend services using Python, FastAPI, Azure OpenAI, Azure AI Services, vector databases, and modern DevOps practices.
• Develops and maintains RAG pipelines, including document ingestion, chunking, embeddings generation, vector indexing, retrieval optimization, and response grounding.
• Implements agentic AI architectures using frameworks such as LangChain, LangGraph, AutoGen, Google Agent SDK, or Model Context Protocol-based integration patterns.
• Integrates AI solutions with enterprise systems, third-party applications, APIs, data platforms, and workflow tools.
• Elevates code into development, test, staging, and production environments following established CI/CD, change control, and release management processes.
• Provides production support for AI applications, including monitoring, troubleshooting, performance tuning, issue resolution, and root cause analysis.
• Participates in design reviews, code reviews, testing reviews, and architecture discussions to ensure scalable, secure, and maintainable AI systems.
• Applies software development methodology and follows architecture, information security, and responsible AI standards.
• Contributes to AI observability and evaluation practices by monitoring model behavior, retrieval quality, latency, accuracy, hallucination risks, and system performance.
• Supports implementation of AI governance controls including PII protection, data privacy, access control, compliance, responsible AI guardrails, and auditability.
• Understands client business functions, technology needs, and enterprise constraints, especially in regulated banking and financial services environments.
• Contributes to optimizing system performance through efficient API design, database optimization, vector search tuning, caching strategies, and scalable infrastructure patterns.
• Supports the integration and maintenance of data pipelines between enterprise systems, vector databases, APIs, and backend AI services, ensuring data accuracy and integrity.
• Maintains and updates technical documentation for AI platforms, backend components, architecture, deployment flows, data pipelines, and operational procedures.
• Applies intermediate to strong knowledge of backend security, AI security, data protection, and cloud-native engineering best practices during solution development.

Qualifications:

• Bachelor’s degree in computer science, Information Technology, or a related field.