layiq

/la·yiq/adjective

worthy; deserving; fitting; suitable.

A role, opportunity, or path that merits attention, time, and pursuit.

Performance Engineer at PDT Partners | LAYIQ

Analyze and understand end-to-end system performance to enhance researcher throughput and velocity.
Work across the OS, kernel, networking stack, storage subsystems, memory hierarchy, and CPU layers to optimize compute resource utilization.
Perform deep-dive analysis using Linux performance tools to identify bottlenecks, latency outliers, and non-scalable patterns.
Read and understand software layers, from application code through language runtimes, system libraries, and kernel code paths, providing suggestions/PRs that optimize critical paths.
Free up capacity, reduce costs, and scale models by improving computational efficiency through tuning, configuration, and architectural changes.
Develop systems to improve performance telemetry and observability
Conduct proof-of-concept evaluations of new performance technologies (new kernel features, alternative system libraries) and contribute to system design decisions.
Work collaboratively with development teams to catch performance regressions, review performance-sensitive code, and share optimization learnings across the organization
Below is a list of skills and experiences we think are relevant. Even if you don't think you're a perfect match, we still encourage you to apply because we are committed to developing our people.
Linux internals expertise: kernel subsystems, scheduling, memory management, virtual memory, cgroups, namespaces, and the networking stack.
Performance tooling: proficiency with perf, eBPF, Ftrace, strace, sysstat, and related tracing/profiling tools. Ability to develop custom tooling when existing tools fall short.
Systems-level optimization: Experience tuning system and application performance via sysctls, scheduler policies, NUMA topology awareness, memory allocators, network tunables, and storage I/O configuration.
Hardware-software interface: Deep understanding of CPU microarchitecture, cache hierarchies, memory subsystems, hardware performance counters, and how software behavior maps to hardware reality.
Versatile coding ability: Comfortable reading and contributing to code across multiple languages (C, C++, Python, Go, Rust, Java) and navigating unfamiliar codebases quickly.
Observability and telemetry: Experience building or integrating monitoring and observability infrastructure (Prometheus, Grafana, OpenTelemetry).
Collaborative and communicative: Ability to analyze performance holistically and to effectively communicate findings, trade-offs, and recommendations to development teams and stakeholders.

Performance Engineer

Employer job description

Why join us

Key Responsibilities

About this listing