Inference performance: Implement and tune speculative decoding, attention kernels, continuous batching, quantization, chunked prefill, and multi-GPU parallel execution.
SLM and adapter lifecycle: Build model and adapter lifecycle management, multi-adapter serving, zero-downtime hot swapping, and resource scheduling.
Production reliability: Implement observability (DCGM, Prometheus, Grafana), tenant isolation, overload protection, failure recovery, and safe rollout and rollback.
Cross-environment deployment: Build portable runtime integrations across NVIDIA and AMD GPU pla4orms, cloud and on-premises environments, and single- or multi-GPU configurations.
Technical Expertise
Model inference internals: Autoregressive generation, prefill vs. decoding, attention architectures, compute- vs. memory-bound execution, numerical precision.
Speculative decoding: Draft-and-verify execution, acceptance/rejection sampling, adaptive speculation, and throughput tradeoffs.
GPU kernels: Flash attention-style kernels, tiling, operator fusion, memory access patterns.
CUDA, HIP, Triton, or CUTLASS proficiency.
KV and prefix caching: Paged KV storage, fragmentation, cache quantization, offloading, cross request prefix reuse, tenant isolation.
Context-window management: Token budgeting, context selection, prompt compression, conversation compaction, sliding window and sparse attention.
Serving and scaling: Continuous batching, chunked prefill, admission control, quantization, multi-GPU parallelism, prefill/decode disaggregation.
Qualifications Required
5+ years engineering, including 3+ years hands-on with GPU systems, distributed inference, or ML serving
Production experience with vLLM, SGLang, or TensorRT-LLM
Strong Python and C++ (C++17/20); ability to read and debug CUDA C++ or HIP kernels
Hands-on GPU profiling and performance optimization
Preferred
Custom GPU kernel development (CUDA, HIP, Triton, CUTLASS)
PyTorch internals — torch. Compile, custom operators, MoE or disaggregated
prefill/decode
LoRA/SLM adapter serving and zero-downtime hot swapping
NVIDIA and AMD Instinct hardware in production
Telemetry with DCGM, AMD SMI, Prometheus, and Grafana
Hiring Pay Range
$175,000 - $218,700
Benefits
In addition to competitive base pay, this position also includes an annual incentive opportunity based on target achievement, pre-IPO stock options, benefits including medical, dental, vision, 401(k) with a match, and more, plus generous paid time off, paid holidays, paid day off for your birthday and other paid leave policies to support employees through all phases of life.
Location preference
USA - CA - Palo Alto
Uniphore is an equal opportunity employer committed to diversity in the workplace. We evaluate qualified applicants without regard to race, color, religion, sex, sexual orientation, disability, veteran status, and other protected characteristics.
For more information on how Uniphore uses AI to unify—and humanize—every enterprise experience, please visit www.uniphore.com.
