Sr. Principal Software Engineer
A Moving Experience.
Who is Cerence AI?
Cerence AI is the global leader in AI for transportation, specialized in building AI and voice-powered companions for cars, two-wheelers, and more that enable people to focus on what matters most. With over 500 million cars shipped with Cerence AI's technology, we partner with leading automakers (such as Volkswagen, Mercedes, Audi, Toyota and many more), mobility providers, and technology companies to power intuitive, integrated experiences that create safer, more connected, and more enjoyable journeys for drivers and passengers alike.
Our Driving Force
Our team is dedicated to pushing the boundaries of AI innovation, working around the globe with headquarters in Burlington, Massachusetts, USA and 16 other offices across Europe, Asia, and North America. We bring together diverse backgrounds, and varied skill sets with the shared goal of advancing the next generation of transportation user experiences. Our culture is customer-centric, collaborative, fast-paced, and fun, with continuous opportunities for learning and development to support your career growth.
Interested in having a significant impact in a dynamic industry with a high-performing global team? We’re looking for an exceptional SeniorPrincipalSoftware Engineer who is ready to drive the future of mobility with us!
Job Description:
What You Will Work On
-
Optimize and deploy high ‑ performance LLM inference pipelines
-
Own inference runtimes across data center, edge, and embedded platforms
-
Push model performance through quantization, kernel fusion, and cache optimization
-
Drive latency and throughput improvements that directly impact production products
-
Enable efficient, reliable deployment without external vendor dependency
Core Responsibilities
Inference Engines & Runtime
- Build deep expertise and ownership of:
- vLLM
- TensorRT‑LLM
- llama.cpp
- QAIRT
-
Extend and tune inference engines using custom CUDA kernels
-
Adapt runtimes for constrained and embedded deployment environments
Quantization & NumericalOptimisation
-
Implement and evaluatequantisationstrategies:
- INT8, INT4, FP4, FP8, mixed precision
- AWQ
- GPTQ
-
Balance accuracy, latency, memory footprint, and throughput
KV Cache Optimization
-
Optimize key–value cache performance through:
- Paging
- Prefix caching
- Cache‑aware memory layout design
-
Reduce memory pressure while sustaining high throughput
Latency & Throughput Optimisation
- Design and tune:
- Batching strategies
- Continuous batching
- Speculative decoding
-
Optimize tail latency and tokens/sec under real production traffic patterns
What Success Looks Like
-
Models deploy efficiently on edge and embedded devices, not just servers
-
Tokens/sec significantly outperform baseline implementations
-
End‑to‑end latency is minimized and predictable
-
Inference cost per request is materially reduced
-
The company is no longer dependent on partners for inference optimization
Required Experience & Skills
Strongly Required
-
Proven experience optimizing ML inference performance in production
-
Deep understanding of GPU architecture and memory hierarchies
-
Hands‑on experience with CUDA and low‑level performance tuning
-
Experience deploying models beyond research environments
Critical Technical Skills
-
Inference engines: vLLM, TensorRT‑LLM, llama.cpp, QAIRT
- CUDA kernel development and profiling
-
Quantisationtechniques: INT8/INT4/FP4/FP8, AWQ, GPTQ
-
KV cacheoptimisationand memory layout design
-
Latencyoptimisation: batching, speculative decoding, continuous batching
Common Problems You’ll Be Solving
-
Deploy efficiently on edge or embedded targets
- Achieve competitive tokens/sec
- Reduce and stabilize inference latency
You will be responsible for closing these gaps, creating a major competitive advantage.
What we offer
We o