Staff MaaS Backend Engineer
BitDeer Technologies Group1 month ago
Singapore, SingaporeStaff+
Responsibilities
- Co-own the end-to-end MaaS system design and maturity roadmap with the Principal Architect.
- Lead technical execution by defining Go and API standards, authoring design decisions, mentoring engineers, and aligning cross-functional teams.
- Build and evolve an inference gateway supporting OpenAI and Anthropic compatibility, streaming, tool calling, structured output, versioning, and deprecation contracts.
- Implement load-aware, model-aware, and prefix-cache-aware routing with circuit breaking, failover, and capacity-aware regional selection.
- Optimize token throughput, KV-cache tiering, time-to-first-token latency, cost per million tokens, and model-serving lifecycle capabilities.
- Integrate deployment tooling, LoRA multiplexing, and cold-start-aware autoscaling with the Kubernetes fleet.
- Scale regional inference pools and an active-active control plane while defining SLOs, load testing, on-call runbooks, and load-shedding behavior.
- Enforce fail-closed authorization, multi-tenant isolation, zero-retention data paths, API-key and OAuth credential lifecycle management, quotas, rate limits, and abuse controls.
- Build exactly-once token metering, a high-volume usage ledger, prepaid spend-cap enforcement, and accurate invoice reconciliation.
- Execute safe brownfield migrations using strangler-style replacements, shadow traffic, and stateful dual writes.
- Deliver end-to-end request tracing and cost telemetry while preventing unauthorized retention of prompts, completions, and PII.
- Carry on-call responsibilities, run blameless incident reviews, and convert outages into structural improvements.
Requirements
- 8+ years of backend engineering experience.
- 3+ years owning a high-traffic, multi-tenant API platform serving paying customers.
- Demonstrated technical leadership, architecture collaboration, rigorous design-document authorship, and effective execution of architectural decisions.
- Experience scaling distributed systems with multi-region active-active deployments, caching, backpressure, and performance engineering.
- Proven experience executing zero-downtime brownfield migrations for stateful systems such as metering or ledgers without regressions or accounting gaps.
- Deep hands-on proficiency with Go-based services and production Kubernetes, including Envoy and GPU-aware scheduling.
- Strong knowledge of PostgreSQL, Redis, and Kafka architectural trade-offs.
- Experience owning end-to-end observability strategies using OpenTelemetry and high-cardinality analytics stores.
- Systems-level understanding of LLM serving, including server-sent-event streaming, KV/prefix caching, TTFT, and throughput trade-offs.
- Experience building reliable exactly-once metering and billing systems that reconcile large event volumes under partial failures.
- Expertise in fail-closed authorization, verified identities, and strict cross-tenant isolation.
- Operational maturity including on-call participation and blameless incident reviews.
Benefits
- Authentic, diverse, inclusive, and respectful work environment.
- Open workspaces and a start-up-oriented culture.
- Opportunity to network with industrial pioneers and contribute to the digital asset industry.
- Direct impact on new projects and the development of processes and systems.
- Personal accountability, autonomy, fast growth, and learning opportunities.
- Welfare benefits and developmental opportunities including training and mentoring.
Tech Stack
Categories