This position is listed on behalf of a partner company, who manages all applications and next steps.
Our partner is looking for a Founding Staff Engineer based in India (Remote).
Responsibilities
Own the design, development, deployment, and ongoing improvement of the entire consumer product, from database architecture and backend services to frontend interfaces and reader-facing experiences.
Build and operate the production systems supporting interactive storytelling, including data models, streaming responses, background jobs, concurrency management, payment processing, credit ledgers, deployment pipelines, and observability.
Design and improve AI-driven experiences that enable users to interact with fictional characters, influence storylines, and maintain coherent narratives across hundreds of conversational turns.
Develop strategies for persistent story memory, contextual retrieval, character-specific knowledge, relationship tracking, and event continuity to ensure that previous interactions meaningfully influence future story developments.
Evaluate and integrate large language models for different tasks, optimizing model selection, orchestration, inference costs, and response latency while maintaining narrative quality.
Build practical benchmarks, test cases, and evaluation systems to measure narrative consistency, character behavior, contextual accuracy, user experience, and potential failure modes.
Design experiments before investing in custom infrastructure, test competing approaches quickly, analyze real-world user behavior, and use evidence to guide product and technical decisions.
Use AI coding agents and development tools to accelerate implementation while maintaining control over architecture, code quality, system integrity, and long-term maintainability.
Establish foundational engineering practices, architectural patterns, documentation, and development standards that enable future engineers to contribute effectively as the team grows.
Ensure that individual story interactions and system events can be reconstructed and analyzed, making it possible to investigate failures, diagnose unexpected model behavior, and improve reliability.
Maintain high standards across performance, responsiveness, typography, interface state, reliability, and narrative immersion to deliver a polished consumer product.
Work closely with the founders, product designer, and senior technical advisers to define priorities, challenge assumptions, make independent technical decisions, and align engineering execution with product strategy.
Evaluate whether to build, buy, or adapt existing tools and AI systems, selecting technologies based on measurable product value, scalability, implementation speed, and cost.
Establish the technical foundation and engineering culture for future hires, with the opportunity to take on broader leadership responsibilities as the organization scales.
Requirements
At least 5 years of relevant professional experience, with substantial hands-on expertise in production software engineering and the development of AI-powered applications.
Demonstrated experience building and operating production systems that use large language models (LLMs) as a core component, including diagnosing failures with real users and implementing effective solutions.
Strong backend engineering and system design capabilities, including database architecture, API design, concurrency, background processing, data integrity, and production reliability.
Experience developing and shipping consumer-facing products end to end, with an understanding of how technical decisions influence usability, engagement, retention, and overall product quality.
Strong knowledge of LLM integration, prompt and context management, memory architectures, retrieval strategies, and model orchestration.
Practical experience designing meaningful AI evaluations and benchmarks, with the ability to measure specific behaviors and failure modes rather than relying solely on generic evaluation scores.
Familiarity with AI coding agents and agent-assisted development workflows, including the ability to review generated code critically and identify architectural, security, and reliability risks.
Ability to design and execute rapid experiments, compare alternative approaches, interpret results, and make data-informed decisions.