Senior Software Engineer, AI Platform

About the Role
We are looking for a Senior Software Engineer, AI platform, who builds products and can see the platform inside them. You will write product features yourself and turn what repeats across products into shared services and libraries that the rest of the team can build on. The platform evolves from real product work, one product at a time, rather than being designed in advance.
Our AI Native Engineering team develops software tools for game teams and internal departments at the company. These tools utilize large language models (LLMs) for a variety of applications, including bug triage, player feedback analysis, and market research, alongside direct-to-consumer web stores for games. Most of these tools follow a similar structure: connect a source system, build a trusted store, integrate LLM or governed logic, and control access permissions. Currently, each product follows its own setup for model configurations, access rules, and safety controls. This is primarily a software engineering role focused on product development rather than infrastructure management.

What You Will Do

• Build product features end-to-end on our internal AI tools using TypeScript or Python, from design through production.
• Identify commonalities across products and transform them into shared services and libraries, including model access and spend, identity, permissions, retrieval, and tool servers. Implement migration to these shared services without halting ongoing deliveries.
• Develop MCP tool servers that serve company data to agents and chat tools, ensuring user permissions are respected before any data reaches the model.
• Introduce relationship-based access control across products to apply consistent access rules for both database queries and vector searches.
• Standardize model access through our LLM gateway to manage model selection, costs, and usage in a centralized manner.
• Implement safety patterns from existing projects across all products, such as prompt-injection handling and sandboxed execution of generated code.
• Simplify the adoption of shared components with clear APIs, versioning, templates, and thorough documentation that other engineers can follow independently.
• Set standards in code reviews, including those involving AI-assisted coding, and mentor fellow engineers in review, pairing, and design processes.
• Take ownership of incidents related to your builds, working alongside DevOps engineers for deployment and operational management.

Requirements
What We Are Looking For

• At least six years of experience in building and managing production software, including developing at least one shared service, library, or internal API relied upon by others.
• Proficiency in TypeScript and Node.js, along with strong skills in Python, as our services are divided across both languages.
• Experience shipping LLM features to production, including retrieval over embeddings and structured output quality checks.
• Proven ability in designing APIs or libraries for other engineers, focusing on versioning, compatibility, and comprehensive documentation.
• Background in building multi-tenant or permission-sensitive systems, with an understanding of access enforcement to prevent unauthorized data exposure.
• Strong system design capabilities, covering service boundaries, data modeling, failure handling, and cost efficiency.
• Hands-on production experience with AWS, including infrastructure as code using Terraform or similar tools, allowing you to oversee the deployment of your services alongside DevOps.
• Consistently write tests and treat CI checks as essential steps, not mere recommendations.
• Excellent written and spoken English, with the ability to convey technical tradeoffs to both product and business stakeholders.
• Comfortable using AI coding tools and verifying their output to ensure ownership of the merged code.

The Stack

• Languages: TypeScript, Node.js, Python 3.11
• Services: Express, FastAPI, Next.js
• AI: OpenAI models and embeddings, LangChain, access control with SpiceDB (currently being introduced)
• Cloud and Delivery: AWS (EC2, ECS Fargate, Lambda, App Runner), Terraform, GitLab, and GitHub
• Data: PostgreSQL (Amazon RDS and Aurora), BigQuery, Amazon OpenSearch Serverless for vector search
• Identity and Access: Okta, OAuth 2.0 with PKCE, relationship-based access control with SpiceDB (currently being introduced)
• Work Tracking: Jira, Confluence

Nice to Have

• Practical experience with relationship-based access control using tools like SpiceDB, OpenFGA, or similar frameworks
• Familiarity with an LLM gateway such as LiteLLM or Amazon Bedrock, and evaluation or tracing tools like Braintrust, Langfuse, or LangSmith
• Experience with agent orchestration frameworks such as LangGraph
• Involvement in a shared platform serving multiple teams or departments, rather than one single product
• Experience in gaming or proficiency in Arabic

Benefits

• Mobile Phone Allowance
• Health Insurance
• Performance Bonus
• Relocation support where applicable