Engineering at Gametime

You will be a key contributor to the Engineering team responsible for building and maintaining the AI and ML platforms that help power the Gametime experience for millions of users. We empower engineers to take full ownership of their code and foster a culture grounded in testing, code reviews, observability, experimentation, and operational excellence. At Gametime, we value collaboration, inclusivity, and the strength of diverse perspectives — creating an environment where people love to build together.

The Role

The Senior AI & ML Engineer is responsible for building and scaling the agentic platform that powers Gametime's conversational experiences and agentic workflows. This person will design, ship, and evaluate LLM-powered features that real customers interact with, touching everything from orchestration and tool use to eval frameworks that keep quality high as the platform evolves. The ideal candidate moves fast without creating tech debt, thrives in ambiguity where goals are clear but implementation is open, and has a track record of putting LLM-powered products into production. 

Key Responsibilities:

• Design, build, and ship LLM-powered features and agentic workflows that serve real Gametime users in production.
• Build and maintain evaluation frameworks, prompt testing pipelines, and regression suites that ensure quality and reliability of AI-powered experiences.
• Contribute to the orchestration layer, including agent routing, tool use, state management, and multi-step workflow coordination.
• Develop and optimize prompt optimization strategies, structured outputs, and LLM integration patterns across the platform.
• Propose architecture decisions and technical designs for review by the team's tech lead, balancing speed with long-term maintainability.
• Collaborate cross-functionally with product, engineering, and data teams to translate customer needs into AI system design.
• Stay current with the rapidly evolving LLM and agentic AI landscape, bringing practical new techniques into the team's toolkit.

Key Competencies:

List the specific competencies (skills, behaviors, and abilities) required for success in this role, organized into key areas. Each competency should have a description that connects directly to the tasks in the job.

Technical Skills:

• Production LLM Engineering: Proven experience shipping LLM-powered features to real users, including prompt engineering, tool use / function calling, structured outputs, and retrieval patterns.
• Evaluation & Testing: Hands-on experience building eval frameworks, prompt regression suites, LLM-as-judge pipelines, or similar quality infrastructure for AI systems.
• Python Proficiency: Deep fluency in Python as the primary development language, including familiarity with LLM SDKs and multi-agent frameworks such as OpenAI Agents SDK.
• Backend & Infrastructure: Solid backend engineering fundamentals including APIs, state management, data pipelines, and cloud infrastructure.
• AI-First Engineering: You use AI agents daily to ship code. Experience with Claude Code, Codex, Cursor, or similar agentic coding tools is required. You direct agents, review their output, and help the team accelerate the development lifecycle.
• AI-Augmented Development Practices: Own and evolve our AI-augmented development practices. You’ll build the context files, guardrails, review processes, and test strategies that make agent-driven development safe and fast.
• Agentic Development Leadership: You don’t just use AI tools - you teach others how. You’ve helped a team adopt agentic workflows, built prompt libraries, or established review processes for agent-generated code.

Interpersonal Skills:

• Collaborative Ownership: Contributes effectively to larger initiatives. Comfortable proposing solutions and iterating based on feedback from a tech lead.
• Clear Communication: Articulates technical decisions, tradeoffs, and progress concisely to both technical and non-technical stakeholders.

Mentorship: You can teach others. We shouldn’t need to teach you AI-first — you should be teaching us.

Problem-Solving and Decision-Making:

• Pragmatic Builder: Balances speed with quality. Ships fast without leaving a trail of tech debt. Knows when to cut corners and when not to.
• High Agency: You move without permission. High agency, low drama. You take responsibility for outcomes in ambiguous situations.

Minimum Qualifications:

Define the minimum educational and experiential requirements necessary to apply for the role.

• Education: Bachelor’s degree in Computer Science, Engineering, or a related field.
• Experience: 5–8 years of professional software engineering experience, with at least 1 year of building LLM-powered or AI/ML systems in production.]
• Other Requirements: [Skills like language proficiency, technical tools]

Preferred Qualifications:

Include any additional qualifications or experience that are not essential but would be beneficial.

• Experience:
• Hands-on experience with multi-agent orchestration patterns (handoffs, agents-as-tools), tool-use frameworks, or complex agentic workflow coordination.
• Prior experience with ML model serving infrastructure, feature stores, or ML data pipelines.

Performance Metrics:

Outline specific measures of success in the role. These should be aligned with the key competencies and job responsibilities.

AI Delivery: Directly contribute to the buildout of the AI build team’s weekly ship goals and leverage learnings to build out platform featuresAI First: Contribute to direct team-related code repos reaching Level 4 by building context files, implementing automated checks to act as agent guardrails, and reducing PR review times through agentic workflows.AI Advisor: Serve as a technical advisor to other teams that are building out agents and agentic workflows. Help teams implement best practices – everything from tracing LLMs and token management to evaluation datasets and building LLMs as a judge.