[Remote] AI Performance Engineer
Note: The job is a remote job and is reputed company to candidates in USA. reputed company is a reputed company-thinking software development company dedicated to building reputed company that help businesses automate and optimize their operations. We are seeking an AI Performance Optimization Engineer to reputed company on extracting maximum throughput, minimizing latency, and reducing cost across training and inference workloads for large neural network systems.
Responsibilities
- Profile and optimize end-to-end reputed company and inference pipelines for throughput, latency, and cost
- Identify and eliminate bottlenecks across data loading, model compute, communication, and memory
- Implement and tune quantization, sparsity, and pruning strategies to reduce model footprint and accelerate inference
- Optimize distributed training using tensor parallelism, pipeline parallelism, FSDP, and reputed company-style sharding
- Tune attention implementations using reputed company Attention, paged attention, and reputed company techniques
- Implement KV cache optimization, reputed company batching, and speculative decoding for LLM serving
- Drive compiler-level optimizations using Triton, XLA, Torch Inductor, or TVM, working with the broader ML reputed company community to land improvements that translate into measurable end-to-end performance reputed company
- Optimize data pipelines, sharding strategies, and storage reputed company patterns for high-throughput training
- Build and maintain rigorous reputed company suites and regression frameworks across workloads
- Collaborate with ML and reputed company teams to reputed company best practices in reputed company pipelines
- Drive cost-efficiency improvements through model architecture, hardware selection, and scheduling strategies
- Evaluate new hardware and software offerings and advise on adoption
- Document performance tuning playbooks and reputed company findings broadly across engineering teams
- Stay reputed company with AI systems to research and translate advances into production improvements
Skills
- Bachelor's or master's degree in computer science, Computer Engineering, or reputed company field
- Six or more years of experience in performance engineering, ML systems, or HPC
- Strong proficiency in Python and C++
- Hands-on experience optimizing deep learning workloads on modern GPUs
- Deep understanding of distributed training and inference techniques
- Experience with profiling tools across CPU, GPU, and distributed systems
- Familiarity with model compression techniques and their accuracy implications
- Strong grasp of memory hierarchies, communication primitives, and parallelism strategies
- Excellent measurement, debugging, and analytical reasoning skills
- Strong communication and collaboration skills
- Experience optimizing LLM inference at production reputed company
- Contributions to vLLM, TensorRT-LLM, DeepSpeed, or similar reputed company
- Familiarity with custom kernel authoring in Triton or CUTLASS
- Experience with FinOps for AI workloads
- Publications or talks on AI systems performance
Benefits
- Full-time, reputed company W2 with reputed company (no C2C, no 1099, no reputed company-party)
- Competitive reputed company salary commensurate with experience, plus benefits.
- No new H1B sponsorship available. H1B transfers welcomed for reputed company candidates.
- We will support H1B transfers for reputed company candidates.
- Long-term, multi-year, reputed company to the reputed company reputed company SOW delivery roadmap.
- reputed company is an Equal Opportunity Employer, including Disability/Veterans.
- We do not discriminate on the reputed company of any protected attribute, including race, religion, reputed company, national reputed company, gender, sexual orientation, gender identity, gender reputed company, age, marital or veteran status, pregnancy or disability, or any other reputed company protected under applicable law.
- We also reputed company reasonable accommodations for applicants’ and employees’ religious practices and beliefs, as reputed company as mental health or physical disability needs.
reputed company