Inference Systems and GPU Evaluation Specialist

Work you will do

• Design technical scenarios in inference optimization, GPU kernels or model-serving architecture.
• Develop reference solutions and assess outputs for correctness, performance reasoning and meaningful systems trade-offs.
• Evaluate relevant quantization, optimizer or distributed-inference choices, using concrete implementation knowledge rather than unsupported performance claims.

Required background and routes

• Research route: six to ten years of relevant work and a PhD, or a master's with a strong research record, alongside current/recent hands‑on expertise.
• Systems route: a relevant computing/electrical engineering bachelor's or higher and substantial ownership at a recognized technology/AI organization, with depth in GPU inference, CUDA kernels, serving systems, quantization or optimizer design.
• Both routes require clear technical writing and independent evaluation of engineering decisions.

Preferred background

• SGLang, TensorRT-LLM, vLLM, Mamba/Mamba2 or Granite models; serving-framework contributions, tensor/expert parallelism, continuous batching and KV-cache optimization; publications or prior technical assessment.

Deliverables

Submit the completed technical artifact or assessment with its supporting evidence, explicit assumptions, reproducible checks where applicable, and concise reasons for each material judgment. Address review findings within the agreed scope.

Location and schedule

Remote assignments are scheduled by agreement, with no guaranteed weekly volume. IXO confirms the applicable timing before work.

Pay and working terms

$105 $180/hr USD. The agreed hourly rate, scope, schedule and acceptance criteria are confirmed before work starts. Applying does not guarantee an assignment. Use public, licensed or otherwise authorized material only; do not submit confidential employer information, personal data or restricted research.