Join Etched as an Inference Software Engineer to build and optimize cutting-edge AI inference systems in a fully in-person team.
Posted by employer 1 year ago
First seen on Joblaze 1 day ago
Last verified on the company career page 1 day ago
What you'll build
- Support porting state-of-the-art models to our architecture
- Build, enhance, and scale our runtime
- Optimize routing and communication layers
- Utilize performance profiling and debugging tools
Must have
- Proficiency in C++ or Rust
- Understanding of performance-sensitive or complex distributed software systems
Nice to have
- Developed low-latency, high-performance applications
- Deep understanding of distributed systems concepts
- Solid grasp of Transformer architectures
Not disclosed in this posting: compensation, seniority, years of experience, visa sponsorship.
Benefits
Joblaze summary
The Inference Software Engineer at Etched focuses on porting advanced models to the company's architecture while enhancing and scaling the runtime for multi-node inference and robust error handling. Key skills include proficiency in C++ or Rust, along with a solid understanding of distributed systems and performance-sensitive software. This role is ideal for experienced engineers with a background in complex software systems and a familiarity with machine learning frameworks like PyTorch or JAX. Etched emphasizes a collaborative environment where engineering and research intersect, fostering a hands-on approach to innovation.
Joblaze insights
Quick facts
- Is the Inference Software Engineer role remote?
- No — this is an on-site role in San Jose, United States.
- Where is the role based?
- Etched is hiring for this position in San Jose, United States.
- What's the tech stack?
- Joblaze extracted these technologies from the posting: C++, JAX, Linux, PyTorch, Rust.
- Is this full-time or contract?
- Full-time for this Inference Software Engineer role at Etched.
From the original posting
Key responsibilities
Support porting state-of-the-art models to our architecture. Help build programming abstractions and testing capabilities to rapidly iterate on model porting.
Build, enhance, and scale our runtime, including multi-node inference, intra-node execution, state management, and robust error handling.
Optimize routing and communication layers using our collectives.
Utilize performance profiling and debugging tools to identify bottlenecks and correctness issues.
You may be a good fit if you have
Proficiency in C++ or Rust.
Understanding of performance-sensitive or complex distributed software systems like Linux internals, accelerator architectures (e.g. GPUs, TPUs), Compilers, or high-speed interconnects (e.g. NVLink, InfiniBand).
Familiarity with PyTorch or JAX.
Ported applications to non-standard accelerator hardware or hardware platforms.
Strong candidates may also have experience with (Nice-to-have qualifications)
Developed low-latency, high-performance applications using both kernel-level and user-space networking stacks.
Deep understanding of distributed systems concepts, algorithms, and challenges, including consensus protocols, consistency models, and communication patterns.
Solid grasp of Transformer architectures, particularly Mixture-of-Experts (MoE).
Built applications with extensive SIMD (Single Instruction, Multiple Data) optimizations for performance-critical paths.
Benefits
Medical, dental, and vision packages with generous premium coverage
$500 per month credit for waiving medical benefits
Housing subsidy of $2.5k per month for those living within walking distance of the office
Daily lunch + dinner in our office
Unlimited compute budget subject to ROI justification
Standard company text repeated across Etched's postings is omitted here.
Similar positions
Explore more