Electronic Arts

Location: Hyderabad | Hybrid 
 Position Type: Temporary Full-Time
 Experience Level: 8+ years of professional systems software engineering experience

About the Team

GameKit Operations (GKO) enables EA’s game creation ecosystem through scalable services and intelligent automation. The GameKit Assistant (GKA) is our AI-driven platform that supports developers, artists, and engineers across game creation products like Shift, Jukebox, and Tryouts, along with supporting COTS products like Jira, Gitlab, Artifactory, Perforce. 

GKA is evolving from a documentation-based chatbot into a Python-powered, context-aware operations assistant that delivers real-time insights and automation at scale. We are expanding our team with engineers who bring strong Python expertise, an understanding of systems design, and a passion for building the connective tissue between AI and production systems.

Role Overview

We are seeking an AI Solutions Engineer with strong Python expertise to design and implement intelligent integrations for the GameKit Assistant. This role is deeply technical and requires hands-on experience building robust, secure, and maintainable backend services in Python.

You will build the interfaces and orchestration logic that allow GKA to communicate with internal tools and commercial platforms through the Model Context Protocol (MCP) and function-calling frameworks. The position involves designing schema-driven APIs, implementing automation pipelines, and collaborating across teams to deliver context-aware AI functionality.

Key Responsibilities

Python Engineering

• Design and implement scalable backend services in Python using frameworks such as FastAPI, Flask, or Django REST Framework.
  
  

• Build and maintain data-access layers, caching mechanisms, and API wrappers that power MCP integrations.
  
  

• Implement schema validation, error handling, and retry logic for reliable automation.
  
  

• Write high-quality, tested, and maintainable code with strong adherence to EA security and performance standards.

MLOps and Pipeline Engineering

• Implement MLOps pipelines for model training, deployment, and monitoring using tools such as Kubeflow, MLflow, SageMaker, and Terraform.
  
  

• Integrate with existing Kubernetes and Docker infrastructure for scalable AI service orchestration.
  
  

• Collaborate with AI Engineering to automate model evaluation and continuous improvement workflows.

RAG and Evaluation Systems

• Implement and maintain retrieval-augmented generation (RAG) systems and internal knowledge bases.
  
  

• Work with vector databases such as Azure Cognitive Search, manage embeddings, chunking, reranking, and retrieval logic.
  
  

• Contribute to performance evaluation frameworks for model outputs using Scikit-learn, PyTorch, or TensorFlow for metrics integration (no model training expected).

AI and MCP Integration

• Develop and maintain MCP wrappers for key GameKit products (Shift, Jukebox, Perforce).
  
  

• Implement function calling and orchestration logic that connects multiple systems to provide contextual insights.
  
  

• Prototype integrations with commercial MCPs (GitLab, Jira, Confluence) to validate interoperability.
  
  

• Contribute to evaluation pipelines to measure assistant accuracy and API reliability.
  
  

Systems and Platform Engineering

• Apply systems engineering principles to design integrations that are modular, observable, and easy to maintain.
  
  

• Work with ArgoCD, Kubernetes, and Docker to deploy and monitor services.
  
  

• Implement metrics, logging, and alerting for all automation endpoints using tools such as Grafana and Prometheus.
  
  

• Ensure integrations comply with EA’s authentication, authorization, and data-governance policies.

• Participate in system design discussions focused on how to bring models “alive” within production pipelines.
  
  

• Design end-to-end integrations that bridge AI orchestration, MLOps, and backend infrastructure for reliability and scale.

• 
  
  

Collaboration and Enablement

• Partner with AI, Ops, and Product Engineering teams to define schemas, error models, and test suites.
  
  

• Mentor peers on Python best practices, performance tuning, and secure API design.
  
  

• Document workflows, integration standards, and technical guidelines for broader adoption.
  
  

Qualifications and Experience

• 8+ years of experience in Python engineering, with exposure to machine learning and MLOps ecosystems (Kubeflow, MLflow, SageMaker, Terraform). 

• Advanced understanding of RESTful APIs, OpenAPI/Swagger, and schema-driven design.
  
  

• Proven experience integrating external APIs and designing resilient service-to-service communication.
  
  

• Solid understanding of authentication frameworks (OAuth2, JWT) and secure credential handling.
  
  

• Experience with CI/CD pipelines, Git, and cloud deployment environments.
  
  

• Exposure to observability stacks (Prometheus, Grafana, ELK) and debugging production systems.
  
  

• Working knowledge of Docker, Kubernetes,ArgoCD and containerized deployments for ML or AI-based systems.
  
  

• Familiarity with RAG architectures, embedding models, and vector databases (e.g., Azure Cognitive Search, Pinecone, Weaviate).
  
  

• Awareness of evaluation frameworks such as Scikit-learn, PyTorch, or TensorFlow, with the ability to integrate metrics or run validation jobs (not model training).
  
  

• Experience contributing to AI pipeline design and integrating models into production systems.

• Bonus: prior work with MCPs, OpenAI, or enterprise automation platforms such as ServiceNow or Power Automate.
  
  

Who You Are

• A Python enthusiast who writes clean, well-tested, and performant code.
  
  

• A systems thinker who enjoys solving complex integration and orchestration challenges.
  
  

• A collaborative engineer who values documentation, mentoring, and teamwork.
  
  

• Curious about AI enablement and motivated by turning complex workflows into simple, reliable automation.