ML Systems Engineer, Inference Benchmarking

CommonAI CIC

. Build and maintain reproducible LLM serving workloads, serving configurations and benchmark tools .

Posted 10/23/2026full-timeCambridge • United KingdomMid-LevelSenior💰 £60,000 - £105,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and maintaining LLM serving workloads, with a strong focus on performance benchmarking and analysis. Proficient in collaborating with engineers to ensure reproducibility and relevance of benchmarks as technology evolves.

Highest-signal resume keywords

LLM Inference ExperienceBenchmark Tool DevelopmentPerformance AnalysisAI Coding Agent UtilizationCollaboration with Engineers

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Machine Learning SystemsPerformance BenchmarksWorkload EvaluationSoftware DebuggingData TransformationLong-Context WorkloadsAgentic ApplicationsTrace AnalysisQuality EvaluationReproducible Comparisons

Soft Skills

Attention to DetailJudgment in Code Validation

Tools & Technologies

VLLMSGLangBenchmark Suite

Industry Keywords

Inference ServicesWorkload-Driven SystemsApplication QualityService RequirementsHybrid Work

About the role

Key responsibilities & impact

Build and maintain reproducible LLM serving workloads, serving configurations and benchmark tools
Develop long-context and agentic workloads using suitable existing software
Characterise request arrivals, prompt and output lengths, caching, batching, tool interactions and request dependencies
Define performance measures alongside application-quality and service requirements
Work with measurement engineers to reproduce workloads on physical systems
Collaborate with simulator engineers to develop workload representations preserving important behaviour and dependencies
Investigate how workload and serving-configuration changes affect conclusions
Keep the benchmark suite relevant as inference technology and workloads evolve
Document datasets, model and software versions, configurations, provenance and permitted use
Compare workload performance across systems under agreed application-quality and service requirements
Help engineers and investors understand infrastructure choices for particular applications

Requirements

What you’ll need

Experience building or evaluating ML systems, inference services, performance benchmarks or comparable workload-driven systems
Strong practical software skills for constructing reliable benchmark tools, analysing results and debugging interactions between applications and infrastructure
Understanding of LLM inference and an interest in how serving choices affect performance and output quality
Care in designing reproducible comparisons and interpreting results against stated application requirements
Practical experience using AI coding agents, with the judgement to validate generated code, data transformations and evaluations
Experience with vLLM, SGLang or similar serving software, long-context workloads, agentic applications, trace analysis or quality evaluation would be valuable
Ability to work with LLM serving; other forms of inference may be possible later
Relevant postgraduate study is useful but qualifications are secondary to experience and work quality
Applicants must be based in the UK or attend Cambridge as agreed for hybrid work

Benefits

Comp & perks

Competitive salary package, including pension and benefits
Professional development opportunities
Networking opportunities with influential figures from across the tech sector and academia
Substantial tooling budget for frontier models and coding agents
Collaborative and supportive work environment
High-impact opportunity in a growing organisation
Vibrant office environment near Cambridge train station
Hybrid working with Cambridge attendance agreed individually
Permanent employment, part-time arrangements and consultancy options
Flexible start date
Inclusive and diverse workplace