Haystack
← Back to Jobs
Other
TRTrebecon LLC logo

AI System Performance & Benchmarking Engineer -- W2 Profiles -- Onsite

Trebecon LLCAtlanta, GA🇺🇸United StatesPosted Oct 14, 2026

Quick Overview

Seniority
Mid Senior
Work mode
On Site
Location
Atlanta, GA, United States
Posted
19 hours ago
DockerSQLitePython

Job Description

Role: AI Systems Performance & Benchmarking Engineer
Location: Onsite - Multiple locations to client office
Key responsibilities:
  • Review AgentSysPerf's architecture end to end: benchmark adapters, measurements, analyzers, storage, replay, reporting and dashboards.
  • Review state persistence, container lifecycle, concurrency and the AgentInvoker protocol implementation.
  • Integrate up to 4 new agentic benchmarks (e.g., τ-bench, BrowseComp, GAIA, BFCL). This includes configuration, CLI execution, model/runtime integration, metrics capture and results persistence.
  • Measure latency, throughput and resource use on Intel hardware.
  • Improve run variance, repeatability, fault handling and SQLite write concurrency during large sweeps.
  • Add new schema fields (policy hashes, topology IDs, route decisions, resource placement) to the storage and telemetry pipelines.
Must-have skills:
  • Python, Linux internals, Docker, cgroups and Linux perf tools.
  • Hardware profiling.
  • SQLite and OTLP/OpenTelemetry exporters.
  • Benchmarking LLMs or agents, including inference engines and runtime configurations.
Nice to have:
  • Xeon platform tuning.
  • Terminal-Bench.
  • Experience with AgentSysPerf itself.

Similar jobs