Senior Software Engineer, Stack AV
Machine Learning Inference Platform
Autonomous systems for the transportation industry
Open for applications
Autonomous systems for the transportation industry
201-500 employees
Open for applications
201-500 employees
Company mission
To revolutionize the transportation industry through the deployment of advanced autonomous systems.
Role
Who you are
- Education: Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field
- Experience: 4+ years of experience building and operating backend distributed systems end to end
- Strong Data & ML systems fundamentals: data-intensive distributed systems, concurrency, networking and performance profiling
- Hands-on experience with large-scale inference services on GPUs, including KV caches, prefill/decode stages and throughput/latency trade-offs
- Direct experience with inference engines (TensorRT, vLLM, etc) or serving frameworks (Dynamo, Triton or equivalent)
- Technical Skills:
- Strong programming skills in C++, Go, Rust or Python
- Familiarity with deep learning frameworks (PyTorch, etc.) as well as model parallelism
- Familiarity with GPU computing primitives such as CUDA, NCCL, NVLink, and hardware-specific optimizations
- Practical understanding of high-performance networking architectures, including InfiniBand, RoCE, and low-latency cluster communication
- Problem-Solving: Strong analytical and problem-solving skills
- Autonomous vehicles (AV) experience is a bonus
What the job involves
- In the Senior Engineer role, you will own meaningful subsystems of Stack AV's inference platform and drive them from design through production
- You will be the go-to engineer for one or more areas such as model onboarding, serving APIs, metering, observability, performance optimization, or tenant isolation
- The role requires strong hands-on implementation, production debugging, thoughtful design, and the ability to mentor engineers while keeping delivery moving
- Own technical design and delivery of subsystems in a high-throughput, low-latency inference platform capable of handling multi-tenant, enterprise-grade inference workloads
- Develop robust API layers (gRPC, WebSockets, REST, etc.) and developer SDKs that abstract complex distributed inference orchestration into seamless, reliable token streams
- Build and harden a multi-tenant control plane to enable accurate metering, rate limiting, quotas, tenant isolation and noisy-neighbor fairness across the platform
- Optimize inference performance across the entire system stack, including the model engine layer
- Build observability and SLOs to gain insights into system economics, cache-hit rates, GPU utilization and cost accounting per model and per tenant
- Partner with product and infrastructure teams on model onboarding, capacity planning, external API contracts and customer adoption
- Decompose ambiguous work, drive issues to closure, and raise the engineering bar through code quality, reviews, testing, and mentoring
Our take
Driver shortages, decelerating efficiency and broad safety concerns have plagued the US trucking industry for some time now. High operating costs paired with increasingly scrutinized high emissions are leading to concern over the future of the logistics and goods transport market. Stack AV’s autonomous trucking solution aims to lighten the load on these issues, utilizing AI to build smart supply chains and autonomous driving systems.
Its founding team has long been exploring the possibilities of autonomous transport through combined experience with Uber and Google smart cars and shared founding roles at Argo AI. This similar company disbanded in 2022 after it failed to become profitable for shareholders. Hopefully, however, the launch of Stack AV will balance the founders' decades of experience and the hard lessons learnt from the failed predecessor company, opening the road to new ways to make autonomous driving tech a sustainable investment.
With a staggering $1 billion investment from SoftBank in 2023, the company is well-armoured for the time being. Its main competitor is Aurora, which underwent a successful IPO in 2021 but never achieved this high level of early funding. It’s a promising start, then for the Argo AI veterans' venture.
Kirsty
Company Specialist at Welcome to the Jungle
Company
Funding (1 round)
Sep 2023
$1bn
SERIES A
Total funding: $1bn
Company HQ
Downtown, Pittsburgh, PA
Leadership
Brian Salesky
(Co-Founder & CEO)Previously CEO of Argo AI, Director of Hardware Development for self-driving cars at Google, Principal Commercialization Specialist at the National Robotics Engineering Center, and Technical Program Manager at Google.
Peter Rander
(Co-Founder & President)Previously President and Co-Founder at Argo AI, Engineering Lead at Uber and Principal Commercialization Specialist at the National Robotics Engineering Center.
Share this job
View 9 more jobs at Stack AV