Senior Backend Engineer (AI Product)

We’re looking for a Senior Backend Engineer to become the first engineering hire on a new product. You’ll play a key role in shaping the product’s technical foundation, making architectural decisions, and owning backend development end-to-end.

You’ll join us at an exciting early stage as we build an AI orchestration platform — a single interface with a unified token balance across dozens of AI models. Our MVP is focused on image and video generation, with text chat and AI agents planned as the next major milestones.
As one of the first engineers on the team, you’ll have a significant impact on the product architecture, technology choices, and engineering culture from day one. What you’ll bring:

Core engineering:

• 4+ years of commercial experience in backend development.
• Strong experience with Go, or solid backend expertise in another statically typed language (Java, Kotlin, C#, Rust, or TypeScript) with a willingness to transition to Go from day one.
• Hands-on experience designing and building backend services that operate under real production load, with a solid understanding of architectural trade-offs and decision-making.
• Strong API design skills (REST, gRPC) with a focus on maintainability, backward compatibility, and building APIs consumed by mobile applications.
• Experience integrating third-party APIs, including handling retries, idempotency, rate limiting, and graceful recovery from partial failures.

Data & Infrastructure:

• Strong knowledge of PostgreSQL, including transactions, isolation levels, indexing, and maintaining data consistency.
• Experience with asynchronous processing and messaging systems such as SQS, Redis, Kafka, Temporal, or similar technologies.
• Experience working with cloud platforms (AWS or GCP), Docker, and modern CI/CD pipelines.
• Practical experience with observability tools and practices, including metrics, logging, tracing, and independently debugging production issues. Experience with VictoriaMetrics, Grafana, and Sentry is a plus.

Nice to have:

• Production experience with generative models (fal.ai, Replicate, Runway, Flux, OpenAI, Anthropic).
• Background in systems where the backend handles money — billing, balances, subscriptions, payment providers.
• Experience with media pipelines: large files, CDN, transcoding.
• B2C products with paid acquisition and an understanding of unit economics.
• Streaming protocols (SSE/WebSocket), Kubernetes, Kafka.
• Early-stage startup experience or a personal project shipped to real users.

Working Environment:

• Ability to quickly ramp up on an existing codebase and build on top of it rather than rewriting it from scratch.
• Comfortable working in a fast-paced, iterative environment where the product is pre-PMF (Product-Market Fit) and priorities evolve as hypotheses are validated.
• Ready to take ownership as the first Product Engineer, driving solutions end-to-end and owning the entire development lifecycle.

What you’ll do:

• Build the orchestration core — a unified layer on top of multiple AI providers with failover, retries, rate limiting, and the ability to onboard a new model in days rather than weeks.
• Own the API contracts consumed by the Flutter client — stability, versioning, and clear error handling.
• Build the media pipeline for storing and delivering generated assets (S3/CDN) with cost control.
• Keep the system reliable under paid-traffic spikes: metrics, tracing, and per-provider alerting.
• Implement usage accounting: per-generation cost tracking, integration with the core billing service, and idempotent charging with no double-spend or race conditions.
• Design the async generation pipeline: long-running job queues (from 10 seconds to 10+ minutes), provider webhooks, delivery guarantees, and recovery from failures.