Senior Software Engineer, AI Platform

About the Role
We are passionate about creating engaging gaming experiences that delight millions of players worldwide. We are looking for a Senior Software Engineer, AI platform, who can build products and comprehend the platform inside them. In this position, you will write product features yourself while transforming repetitive tasks across products into shared services and libraries for the broader team. Our approach emphasizes building the platform through real product work, one product at a time, rather than ahead of it.

The AI Native Engineering team develops software for game teams and internal departments, creating tools that utilize large language models (LLMs) for various purposes, such as bug triage, player feedback analysis, market and company research, and contract analytics. Additionally, we support direct-to-consumer web stores for games. Each product currently follows its unique approach for connections, model setups, access rules, and safety controls.

What You Will Do

• Build product features end-to-end on our internal AI tools using TypeScript or Python, from design through production.
• Identify common functionalities across our products and turn them into shared services and libraries, including model access and spend, identity and permissions, retrieval, tool servers, and controls around LLM calls. Transition products to these shared services progressively without halting delivery.
• Create MCP tool servers that securely expose company data to agents and chat tools while enforcing user permissions before any data is processed by the model.
• Implement relationship-based access control across products, ensuring access rules are defined once and applied consistently to both database queries and vector searches.
• Standardize model access through our LLM gateway, centralizing model choices, costs, and usage management rather than duplicating them across repositories.
• Extend safety patterns present in individual projects to all products, including prompt-injection handling, kill switches, sandboxed execution of generated code, and restricted data access.
• Ensure shared components are easy to adopt by providing clear APIs, versioning, templates, and thorough documentation that other engineers can follow independently.
• Set standards in code review, including reviewing AI-assisted code, and mentor engineers through review, pairing, and design discussions.
• Own incident management related to your work and collaborate with DevOps engineers on deployment and operational aspects.

What We Are Looking For

• Six or more years of experience building and running production software, with a focus on at least one shared service, library, or internal API relied upon by other engineers or teams.
• Strong proficiency in TypeScript and Node.js, along with solid Python skills, given that our services are distributed across both.
• Experience shipping LLM features to production, such as retrieval over embeddings, tool calling, structured output, and quality checks for output.
• Proven ability in designing APIs or libraries for other engineers to use, with a strong emphasis on versioning, compatibility, safe defaults, and documentation.
• Background in building multi-tenant or permission-sensitive systems, with the ability to enforce access rules to prevent unauthorized data exposure.
• Solid understanding of system design, including service boundaries, data modeling, failure handling, idempotency, and cost management.
• Production experience on AWS, including infrastructure as code using Terraform or similar tools, sufficient to manage how your services integrate with DevOps practices.
• Commitment to writing tests as part of development work and treat CI checks as essential gates rather than mere suggestions.
• Clear communication skills in both written and spoken English, able to explain technical trade-offs to product and business stakeholders.
• Familiarity with AI coding tools, capable of verifying AI-generated output and taking ownership of 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 (designed, being introduced)
• Cloud and Delivery: AWS (EC2, ECS Fargate, Lambda, App Runner, S3, CloudFront), Terraform, GitLab, 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 (designed, being introduced)
• Work Tracking: Jira, Confluence

Nice to Have

• Experience with relationship-based access control in practice, using tools like SpiceDB or OpenFGA
• Familiarity with LLM gateways such as LiteLLM or Amazon Bedrock, along with evaluation or tracing tools like Braintrust, Langfuse, or LangSmith
• Experience utilizing an agent orchestration framework such as LangGraph
• Background in developing a shared platform that served multiple teams or departments instead of a single product
• Interest or experience in games, or proficiency in Arabic

Benefits

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