Principal Machine Learning Engineer, Inference

Inworld AI

. Build first-party speech models and serve LLMs for realtime, consumer-facing applications .

Posted 10/14/2026full-timeRemote • United KingdomLead💰 £140,000 - £200,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

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

Demonstrates expertise in building and optimizing first-party speech models and LLMs for real-time applications, with a strong focus on performance, scalability, and production deployment. Proficient in systems programming and collaboration with research and engineering teams to deliver high-impact solutions.

Highest-signal resume keywords

C++ ProficiencyCUDA OptimizationKubernetes ExperienceDeep Understanding of vLLMPhD in CS, Physics, or Math

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

Model ServingInference FrameworksQuantizationDistillationCaching StrategiesPaged AttentionSpeculative DecodingMulti-GPU InferenceSystems ProgrammingPerformance Profiling

Tools & Technologies

KubernetesRayNVIDIA GPUsLoad BalancingModular APIs

Industry Keywords

Real-Time ApplicationsHigh-Volume WorkloadsOpen-Source Inference EnginesProduction SystemsConcurrent Connections

Tech Stack

Tools & technologies

Distributed SystemsKubernetesNode.jsPythonRayRustC++

About the role

Key responsibilities & impact

Build first-party speech models and serve LLMs for realtime, consumer-facing applications
Develop and operate inference behind modular APIs for high-volume, realtime workloads
Optimize model serving for latency, throughput, and performance at scale
Containerize models and transition them from research into reliable production systems
Work with inference frameworks, distributed systems, Kubernetes, Ray, load balancing, and multi-GPU/multi-node infrastructure
Design benchmarks or prototypes to clarify ambiguous technical problems
Profile and optimize code running on NVIDIA GPUs
Contribute to systems programming, open-source inference engines, or technical write-ups
Collaborate with research and engineering teams to ship stable, high-impact systems

Requirements

What you’ll need

Deep understanding of modern serving frameworks and techniques such as vLLM or TRT-LLM
Hands-on experience with quantization, distillation, caching strategies, continuous batching, paged attention, and speculative decoding
Proficiency in C++, CUDA, Rust, or highly optimized Python
Ability to profile code and optimize NVIDIA GPU performance
Experience with Kubernetes, Ray, custom load balancing, multi-GPU/multi-node inference, and handling thousands of concurrent connections
Non-trivial systems programming projects, open-source contributions to major inference engines, or deep-dive technical write-ups
Ability to take a model from research through production deployment and reliability
PhD in CS, Physics, or Math, or equivalent practical experience building backend or ML systems
Must already have the legal right to work in the United Kingdom
Visa sponsorship is not available for this role

Benefits

Comp & perks

Equity
Benefits
Potential future U.S. visa and relocation support for relocation to the San Francisco Bay Area, subject to business needs and applicable legal and work authorization requirements