Senior Inference Engineer, AGI

• Partner with research scientists to make model architectures servable from inception —

surfacing the latency, memory, and cost implications of architecture choices before they are

• Implement and optimize the inference path for large-scale multimodal models — attention

and KV-cache mechanisms, multimodal/autoregressive decoding, and the compute

primitives on the critical path

Apply efficiency techniques across the stack — quantization (per-tensor/per-channel/per-

group, INT8/FP8/BF16), speculative decoding, operator fusion, and paged KV-cache — and

• Develop and tune high-performance kernels for critical operations where off-the-shelf

implementations leave performance on the table, integrating them into production serving

• Profile end-to-end performance with tools such as Nsight Compute/Systems and roofline

analysis to identify and eliminate bottlenecks in large-scale inference workloads

• Own the real-time serving path for streaming multimodal conversational AI, meeting sub-

• Build and tune continuous batching, scheduling, and preemption to balance throughput

• Customize production serving frameworks (e.g., vLLM, PyTorch) for real-time streaming

generative models that fall outside standard LLM serving patterns — sustained low-latency

• Implement multi-GPU inference (tensor parallelism, collective communication) for latency-

• Establish latency, throughput, and cost benchmarking, and publish the operational metrics

that gate deployment

• Build and scale the offline inference systems behind post-training — high-throughput rollout

• Ensure train/serve consistency – that the inference path used in RL and evaluation

faithfully matches production online behavior (e.g., parity across sampling and logit

• Work with the evaluation team to enable offline inference that captures the quality

dimensions unique to real-time conversation — latency sensitivity, audio quality, and

• 3+ years of building machine learning models for business application experience
• PhD, or Master's degree and 6+ years of applied research experience
• Experience programming in Java, C++, Python or related language
• Experience with neural deep learning methods and machine learning
• 2+ years of hands-on experience optimizing inference for neural models — not just using inference frameworks, but profiling and improving them
• Strong understanding of deep learning architectures (transformers, attention mechanisms, autoregressive decoding) and their application to speech/audio or other multimodal domains
• Production track record delivering latency-constrained, real-time inference systems under concurrent load
• Experience with GPU performance optimization — memory hierarchy, occupancy, KV-cache management, and the accelerator programming model
• Demonstrated ownership of a technical area — driving execution for a workstream and collaborating effectively across scientists and engineers
• Experience with modeling tools such as R, scikit-learn, Spark MLLib, MxNet, Tensorflow, numpy, scipy etc.
• Experience with production LLM/multimodal serving internals (e.g., vLLM, TensorRT-LLM): scheduler, batching, block manager, sampler customization
• Hands-on experience building real-time or streaming AI systems — speech, audio, or video — with hard latency budgets
• Experience authoring custom GPU kernels (CUTLASS, Triton, raw CUDA/PTX), fused attention (FlashAttention-style), or quantized GEMM
• Familiarity with model-compression and efficiency techniques — quantization, pruning, distillation, speculative decoding, long-context optimization
• Experience building offline inference or rollout/reward-serving infrastructure for reinforcement learning or large-scale evaluation
• Experience with distributed training and post-training pipelines (SFT through RL) — parallelism strategies, training stability, and multi-accelerator communication (NCCL, NVLink)
• Familiarity with multiple hardware backends (NVIDIA GPU, AWS Neuron/Trainium, edge accelerators) and how architecture choices affect inference latency, memory, and cost
• Background in speech-to-speech or audio generative models (codec models, autoregressive audio generation), speech recognition, or speech synthesis
• Experience shipping research to production at scale — models serving real users, not just benchmark results
• Contributions to open-source inference/kernel projects (vLLM, CUTLASS, FlashAttention, TensorRT-LLM, Triton, or similar)

Los Angeles County applicants: Job duties for this position include: work safely and cooperatively with other employees, supervisors, and staff; adhere to standards of excellence despite stressful conditions; communicate effectively and respectfully with employees, supervisors, and staff to ensure exceptional customer service; and follow all federal, state, and local laws and Company policies. Criminal history may have a direct, adverse, and negative relationship with some of the material job duties of this position.

These include the duties and responsibilities listed above, as well as the abilities to adhere to company policies, exercise sound judgment, effectively manage stress and work safely and respectfully with others, exhibit trustworthiness and professionalism, and safeguard business operations and the Company’s reputation. Pursuant to the Los Angeles County Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.

Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.

The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, and parental leave.

Learn more about our benefits at https://amazon.jobs/en/benefits.

USA, CA, Sunnyvale – 192,200.00 - 260,000.00 USD annually

USA, MA, Boston – 167,100.00 - 226,100.00 USD annually

USA, WA, Seattle – 167,100.00 - 226,100.00 USD annually