Backend Engineer LLM Inference
Farcana is a Web3 team-based ability hero shooter featuring fast-paced 4v4 PvP battles, unique heroes, esports, NFTs, and Bitcoin-backed rewards.
Funding history
About Farcana
Farcana develops and operates a sci-fi 4v4 PvP hero shooter with ability-based gameplay, competitive arenas, player-driven narrative, in-game economies, esports integration, NFT assets, and Bitcoin-backed rewards. Its platform also provides Web3 services for FAR token holders, including account assets, token staking, vesting, and airdrop participation. The organization primarily serves players, NFT holders, token holders, and participants in its gaming ecosystem.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will own backend architecture and build distributed services in Go, TypeScript or JavaScript, and Python where appropriate. You will develop OpenAI-compatible streaming APIs, route inference requests, optimize service performance, design data systems, implement authentication and billing integrations, test production systems, and mentor engineers.
Requirements
- 5+ years of professional backend engineering experience
- Commercial experience with Go and TypeScript or JavaScript using Node.js
- Experience building and operating distributed systems
- Understanding of consistency, fault tolerance, and service-to-service communication
- Deep understanding of Go concurrency and the Node.js event loop and async model
- Strong PostgreSQL knowledge including schema design, indexing, query optimization, transactions, isolation levels, and locking
- Experience with Redis, Valkey, or similar in-memory stores
- Experience with LLM inference backends or understanding of token streaming and long-running requests
- Experience building streaming APIs using SSE or WebSockets
- Understanding of OpenAI-compatible API design
- Experience with request routing, load balancing, backpressure, and admission control
- Experience designing REST or gRPC APIs
- Experience building authentication systems with JWT, Auth0, or similar
- Experience leading systems or major features end to end
- Experience resolving complex production issues
- Familiarity with vLLM, SGLang, or TGI
- Experience with inference scheduling, tenant isolation, usage metering, billing, Stripe, S3-compatible storage, Cloudflare R2, or developer-facing APIs
Responsibilities
- Design, build, and maintain backend services in Go, TypeScript or JavaScript, and Python
- Build and scale reliable distributed systems
- Own features from design documentation through implementation, testing, and release
- Identify technical debt, bottlenecks, and reliability risks
- Design and maintain OpenAI-compatible APIs for chat completions, streaming, and tool calls
- Build token streaming over SSE and WebSockets
- Build request routing and load balancing across inference backends
- Implement backpressure, queueing, and admission control
- Design REST and gRPC interfaces between internal services
- Design and optimize PostgreSQL data models
- Use Redis or Valkey for caching, state, and high-performance workloads
- Integrate S3-compatible storage and Cloudflare R2
- Build authentication and authorization flows with Auth0 and JWT
- Build rate limiting and usage metering for multi-tenant APIs
- Build reliable Stripe and third-party integrations
- Optimize latency, throughput, and resource usage
- Write automated tests
- Mentor engineers and contribute to code reviews and design discussions
Benefits
- Performance-based incentives
- 24 days annual leave plus public holidays
- Health insurance
