Inference Performance Engineer - MaaS

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 Inference Performance Engineer to make Bitdeer AI's MaaS platform's benchmarks, capacity plans, and cost projections trustworthy proxies for what customers actually run in production. Today, load tests are built on prompt and output length assumptions and concurrency patterns that were reasonable a quarter ago but no longer match the traffic mix flowing through chat, completion, and embedding endpoints — the result is GPU fleets sized against a workload that doesn't exist, cost-per-token figures that surprise finance at quarter close, and latency percentile dashboards that different teams calculate differently and therefore don't trust. This role exists to close that gap: characterizing real production traffic shapes, keeping benchmarking harnesses honest against that reality, and turning the results into capacity and unit-economics numbers the business can plan around with confidence. The person who thrives here is a rigorous, data-first systems thinker who is equally comfortable pulling apart a token-length histogram, arguing with a serving-stack engineer about tail latency, and explaining a GPU-hour cost model to finance — someone who treats every metric definition as a contract other teams will build on, not a throwaway number.

What you will be responsible for:

• Traffic and Workload Characterization: Continuously profile real production request streams across chat, completions, embeddings, and fine-tuning endpoints to build and maintain statistical models of prompt length, output length, concurrency, and burstiness by model and customer segment. Surface how these distributions shift over time and by tenant so that benchmarking, capacity, and pricing decisions are grounded in what the platform actually serves rather than stale assumptions. Package these findings into reusable traffic profiles other teams can pull from directly.
• Harness-to-Production Fidelity: Own the validation loop between internal load-testing and benchmarking harnesses and live production behavior, auditing synthetic workload generators against the traffic profiles you maintain and flagging drift before it corrupts a capacity or optimization decision. Work with the inference serving team to update harness configurations, request mixes, and concurrency patterns whenever production shifts. Treat every benchmark result as suspect until it has been reconciled against real telemetry.
• Capacity Planning and Unit Economics: Translate workload characterization and GPU utilization data into capacity forecasts and cost-per-token or cost-per-request models that inform fleet sizing, reservation versus on-demand mix, and pricing strategy for the MaaS product. Partner with infrastructure and finance teams to reconcile modeled costs against actual cloud and hardware spend, and maintain the analytical models that answer how many GPUs are needed and what they will cost with defensible numbers rather than gut calls.
• Metric Definition Ownership: Define and maintain the canonical definitions for latency percentiles (time-to-first-token, inter-token latency, end-to-end), throughput, and utilization metrics used across engineering, product, and leadership dashboards, resolving disagreements between teams that compute the same-sounding metric differently. Document instrumentation requirements, aggregation windows, and edge-case handling so metric definitions stay stable as the platform and model catalog evolve, and audit dashboards for silent drift from the documented standard.
• Cross-Team Performance Reporting: Build and maintain the dashboards, reports, and postmortem inputs that give engineering, product, and leadership a shared, trustworthy view of inference performance and cost trends, translating raw telemetry into decision-ready summaries. Act as the go-to reviewer whenever a performance or cost claim needs sanity-checking before it reaches a roadmap, pricing, or capacity decision, and coach other teams on correctly interpreting percentile and cost metrics.

How you will stand out:

• Bring 5+ years of experience in performance engineering, capacity planning, or applied ML systems work on large-scale, GPU-backed or otherwise latency-sensitive distributed services, with at least part of that time spent directly on LLM or ML inference workloads.
• Demonstrate hands-on experience characterizing production traffic statistically — building distributions of request rate, prompt and output token length, concurrency, and burstiness — using tools such as Python/pandas, SQL, Spark, or a comparable data-analysis stack.
• Show working knowledge of modern LLM inference internals, including continuous batching, KV-cache management, and prefill/decode scheduling, and familiarity with serving frameworks such as vLLM, TensorRT-LLM, SGLang, or Triton Inference Server, sufficient to judge whether a benchmarking harness reflects reality.
• Have experience designing, running, or auditing load-testing and benchmarking tooling (e.g., k6, Locust, custom load generators, or MLPerf-style suites) and reconciling their output against live production telemetry rather than treating benchmark numbers as ground truth.
• Be comfortable partnering with finance/FinOps and infrastructure teams on GPU utilization and cost-per-token or cost-per-request modeling, including reasoning about on-demand, reserved, and spot capacity trade-offs.
• Bring fluency with observability stacks such as Prometheus, Grafana, and distributed tracing tools, and a track record of defining metrics (latency percentiles, throughput, time-to-first-token) that hold up as the single source of truth across multiple teams.

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