AI-Powered Developer Platform: Design and build the infrastructure that enables AI agents to participate in software development, from initial task intake through implementation, testing, and pull request review.

Development Environments: Build and maintain reproducible local development stacks and cloud-based coding environments that allow engineers and agents to run services and tests reliably without extensive manual setup.

Autonomous Coding Agents: Integrate and orchestrate AI agents that transform tickets, bug reports, and other requests into validated code changes and review-ready pull requests, including browser and native application testing where appropriate.

Agent Selection and Orchestration: Evaluate, select, and integrate open-source and commercial coding agents. Configure triggers, credentials, contextual information, tools, and execution workflows to ensure agents operate effectively and efficiently.

Workflow Integrations: Connect agent workflows to tools and systems such as Slack, Jira, GitHub, Datadog, and incident management platforms, enabling production alerts and operational issues to initiate potential fixes.

Infrastructure and Automation: Develop and improve cloud infrastructure, containers, CI/CD pipelines, and infrastructure-as-code solutions to support reliable, scalable, and repeatable agent execution.

Security and Governance: Establish guardrails governing agent access to data, secrets, and personally identifiable information. Define appropriate permissions, compliance controls, and human-review requirements for a regulated, real-money contest environment.

Continuous Improvement: Identify recurring issues that limit agent effectiveness, including missing context, unreliable tests, insufficient tools, and environment gaps, then address their root causes.

Agent Evaluation and Observability: Measure agent performance across coding and non-coding tasks, track execution quality and costs, and use telemetry and evaluation results to improve reliability and efficiency.

Business-Wide Enablement: Develop reusable agent runtimes, triggers, and safeguards that can support teams beyond engineering, helping other functions adopt automation with appropriate guidance.

Performance Measurement: Improve key indicators such as pull request cycle time, review latency, and the proportion of pull requests authored or reviewed by AI agents.

Cross-Team Collaboration: Work independently while communicating clearly across distributed teams, sharing progress, proactively identifying opportunities, and helping establish effective practices for AI-assisted development.

Professional Experience: At least six years of software engineering experience, including meaningful work in infrastructure, platform engineering, developer experience, or internal tooling.

Advanced AI Agent Usage: Current, hands-on experience using AI coding agents such as Claude Code, Codex, Cursor, or similar tools for at least 90% of your development work. You should understand their limitations and know how to improve their results.

Multi-Agent Orchestration: Experience coordinating multiple agents or delegating work to subagents is highly desirable, particularly when supported by custom skills, hooks, harness configurations, or parallel execution workflows.

Cloud Infrastructure: Strong experience with AWS services and infrastructure, including ECS/Fargate, RDS, Lambda, networking, and IAM.

Infrastructure as Code and Delivery: Practical experience with Terraform, AWS CDK, CloudFormation, or comparable infrastructure-as-code tools, along with containers and CI/CD pipelines that you have built, maintained, or optimized.

Software Development Skills: Ability to contribute directly to TypeScript and Node.js services and work comfortably within existing codebases.

Developer Tooling: Experience building internal platforms, development environments, automation systems, or other engineering tools that achieve real adoption among developers.

Data-Driven Evaluation: Familiarity with assessing AI agents across coding and non-coding tasks, interpreting performance data, and using repeatable evaluations to guide technical decisions.

Autonomy and Initiative: Ability to identify problems independently, move quickly from experimentation to implementation, and proactively improve engineering workflows.

Remote Collaboration: Strong written communication skills and the ability to keep colleagues informed while collaborating across US and Prague time zones.

Preferred Environment Expertise: Experience with sandboxed or ephemeral development environments using Docker, devcontainers, Kubernetes, Nix, or similar technologies.

Preferred Agent Integrations: Experience building Model Context Protocol (MCP) servers or other integrations that enable AI agents to interact securely with real systems and tools.

Preferred Observability Skills: Familiarity with OpenTelemetry, LLM tracing, agent execution telemetry, evaluation frameworks, and cost tracking.

Industry Experience: Experience in a regulated industry, such as gaming or financial technology, is an advantage.

Additional Interest: An enthusiasm for sports is a plus.

Annual Salary: $150,000–$190,000, with final compensation depending on experience and skill level. The stated range may be subject to change.

Potential Equity: Opportunity to earn equity in the company, subject to the applicable terms and eligibility requirements.

Healthcare Coverage: Medical, dental, and vision insurance.

Retirement Planning: Access to 401(k) or other retirement plan options.

Flexible Time Off: Flexible paid time off (PTO).

Team Events: Annual company retreats and team offsites.

Team Engagement: Regular company-wide games featuring cash prizes.

Remote Work: Full-time remote work within the United States.

Professional Impact: The opportunity to build AI-driven engineering infrastructure and contribute to products serving sports fans nationwide.

Growth Environment: Work within a fast-growing organization at the intersection of software engineering, AI automation, and fantasy sports.