Senior Inference Engineer, AGI

We are looking for a Senior Inference Engineer to own inference for real-time multimodal
conversational AI. This is a full-stack inference role: you will work across the entire path a model
takes from research to production shaping model architecture so it is servable building the
real-time runtime that serves it within hard latency budgets and building the offline systems
that train and reinforce it.

You will operate at the boundary of Science and Inference taking frontier-scale speech and
audio models and making them run within real-time latency budgets on production hardware.
You will co-design architectures with scientists to make them inference-friendly from inception
own the low-latency streaming serving path and build the training and reinforcement-learning
infrastructure that closes the loop. You will have the compute data and runway to solve
problems that few teams in the world are positioned to tackle.

As a Senior Engineer you will own a significant area of the inference stack end to end drive its
technical execution contribute to the teams roadmap and work closely with scientists and
hardware partners to ensure our models run fast enough to feel human in real time and at a
cost that makes them viable at scale. You may go deep in one of the areas below while
contributing across the others.

Key job responsibilities
Model Architecture & Inference Co-Design
Partner with research scientists to make model architectures servable from inception
surfacing the latency memory and cost implications of architecture choices before they are
locked in
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
quantify their quality/latency trade-offs
Develop and tune high-performance kernels for critical operations where off-the-shelf
implementations leave performance on the table integrating them into production serving
with minimal overhead
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
Real-Time & Interactive Runtime
Own the real-time serving path for streaming multimodal conversational AI meeting sub-
second streaming latency budgets under concurrent session load
Build and tune continuous batching scheduling and preemption to balance throughput
against per-request latency SLAs for interactive workloads
Customize production serving frameworks (e.g. vLLM PyTorch) for real-time streaming
generative models that fall outside standard LLM serving patterns sustained low-latency
output under concurrent session load
Implement multi-GPU inference (tensor parallelism collective communication) for latency-
critical paths and drive cost toward parity with existing production baselines
Establish latency throughput and cost benchmarking and publish the operational metrics
that gate deployment
Offline Systems: Training RL & Evaluation Infrastructure
Build and scale the offline inference systems behind post-training high-throughput rollout
generation and reward-model serving for reinforcement learning (RL/RLHF/RLAIF)
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
processing)
Work with the evaluation team to enable offline inference that captures the quality
dimensions unique to real-time conversation latency sensitivity audio quality and
interaction naturalness

- 5 years of non-internship professional software development experience
- 5 years of programming with at least one software programming language experience
- 4 years of leading design or architecture (design patterns reliability and scaling) of new and existing systems experience
- Bachelors degree in computer science or equivalent
- Experience as a mentor tech lead or leading an engineering team
- 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 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)

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status disability or other legally protected status.

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 Companys 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 for more information. If the country/region youre applying in isnt 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 CA Sunnyvale - 193300.00 - 261500.00 USD annually
USA MA Boston - 168100.00 - 227400.00 USD annually
USA WA Seattle - 168100.00 - 227400.00 USD annually