The posting
About Bitdeer:
Bitdeer is a world-leading technology company for Bitcoin mining and AI cloud.
Bitdeer is committed to providing comprehensive Bitcoin mining solutions for its customers. Apart from designing industry-leading ASIC chips and manufacturing mining rigs, the Group handles complex processes involved in computing across the value chain. This includes equipment procurement, transport logistics, datacenter design and construction, equipment management, and network and facility operations. Bitdeer also offers advanced cloud capabilities to customers with a high demand for artificial intelligence.
Headquartered in Singapore, Bitdeer operates globally with a diversified 3 GW energy portfolio, and deploys Bitcoin mining and HPC datacenters in the United States, Bhutan, Norway, Canada, Malaysia, and Ethiopia.
About the role
We are seeking an Integration Engineer to build and operate the adapter layer that connects Bitdeer AI's Model-as-a-Service platform to the third-party inference providers we route traffic to alongside our own GPU-hosted models. Today, each upstream provider exposes its own request schema, streaming format, rate-limit behavior, and error taxonomy, which means an outage or partial degradation upstream surfaces as a confusing, inconsistent failure to our customers, and a single vendor's mid-month price change or metering quirk can silently erode margin before finance ever notices. This role owns closing that gap end to end: writing and maintaining provider adapters that normalize capabilities and error semantics into one internal contract, implementing the cost guardrails and circuit breakers that stop a misbehaving or expensive upstream from taking down the platform or the budget, watching provider API contracts for breaking changes before they reach production, and reconciling provider invoices against our own usage telemetry so billing disputes get caught in days rather than quarters. The person who thrives here is equally comfortable reading a provider's changelog line by line and writing the resilience code that assumes that changelog will eventually be wrong.
What you will be responsible for:
- Provider Adapter Development: Build and maintain the adapter layer that connects Bitdeer AI's MaaS gateway to third-party inference providers, translating each vendor's request and response formats, streaming protocols, and authentication schemes into our internal unified interface. Own the full adapter lifecycle from initial integration through version upgrades, deprecations, and eventual sunset, keeping the abstraction clean enough that new providers can be onboarded without touching downstream product code.
- Capability and Error Mapping: Normalize the inconsistent feature sets and error taxonomies exposed by different upstream providers, including context limits, function-calling support, streaming semantics, and rate-limit or timeout codes, into a single predictable contract the rest of the platform can build against. Ensure a customer-facing error always reflects what actually happened upstream rather than a generic pass-through failure, so support and product teams can trust the signal.
- Cost Guardrails and Circuit Breaking: Design and implement automated spend controls and circuit breakers that detect runaway token usage, retry storms, or degraded upstream latency and throttle or fail over before they turn into an outsized invoice or a platform-wide outage. Tune thresholds per provider and per model, and build the tooling that lets on-call engineers trip or reset a breaker with confidence during a live incident.
- Upstream Contract Monitoring: Continuously monitor provider API changelogs, deprecation notices, and live response shapes for breaking changes, and build automated contract tests that catch drift before customer traffic does. Maintain a clear escalation and rollback path for each provider so a surprise upstream change degrades gracefully instead of taking down chat completions or embeddings for every tenant.
- Provider Bill Reconciliation: Reconcile monthly provider invoices against internal usage and metering records at the request level, identifying and resolving discrepancies caused by retries, failed calls, rounding, or provider-side metering bugs. Partner with finance to close the loop quickly so billing disputes are resolved in days rather than becoming a recurring end-of-quarter fire drill.
- Provider Onboarding and Evaluation: Evaluate prospective inference providers for API quality, pricing structure, and reliability track record before they are added to the routing pool, running structured proof-of-concept integrations that stress-test rate limits and failure modes. Provide the technical due diligence that product and finance need before committing platform traffic and revenue to a new vendor.
How you will stand out:
- Bring 4+ years of backend engineering experience building and operating production API integrations, with at least one project involving multiple third-party providers behind a single internal interface.
- Demonstrate hands-on experience with Go and/or a comparable statically-typed backend language, including building HTTP or gRPC clients, retry and backoff logic, and circuit-breaker patterns in production systems.
- Show working knowledge of LLM and inference provider APIs (such as OpenAI-, Anthropic-, or similar-style interfaces) including streaming responses, function calling, and token-based rate limiting, and how these behaviors differ across vendors.
- Have direct experience building or maintaining cost and usage monitoring or alerting for a metered, usage-billed system, ideally including reconciliation against a vendor or partner invoice.
- Be comfortable reading unfamiliar third-party API documentation and changelogs quickly, writing contract or integration tests, and debugging failures that originate outside your own codebase.
- Bring familiarity with observability tooling such as Prometheus, Grafana, or distributed tracing, sufficient to diagnose latency and error-rate regressions introduced by an upstream dependency.
What you will experience working with us:
- A culture that values authenticity and diversity of thoughts and backgrounds;
- An inclusive and respectable environment with open workspaces and exciting start-up spirit;
- Fast-growing company with the chance to network with industrial pioneers and enthusiasts;
- Ability to contribute directly and make an impact on the future of the digital asset industry;
- Involvement in new projects, developing processes/systems;
- Personal accountability, autonomy, fast growth, and learning opportunities;
- Attractive welfare benefits and developmental opportunities such as training and mentoring.
--------------------------------------------------------------------
Bitdeer is committed to providing equal employment opportunities in accordance with country, state, and local laws. Bitdeer does not discriminate against employees or applicants based on conditions such as race, colour, gender identity and/or expression, sexual orientation, marital and/or parental status, religion, political opinion, nationality, ethnic background or social origin, social status, disability, age, indigenous status, and union.
#LI-ST1
