AI Researcher — Inference Optimization
In short AI
Research and development of inference optimization techniques for large machine learning models, improving latency, throughput and cost, with production deployment in collaboration with engineering teams.
Description
- Role
- Design, evaluate and deploy high-performance inference systems for large-scale machine learning models. Develop model-level optimizations (quantization, pruning, KV-cache) and systems-level optimizations (dynamic batching, kernel fusion, multi-GPU inference). Benchmark workloads across hardware accelerators and work with engineering teams to deploy optimized pipelines in production.
- Requirements
- Strong background in machine learning, deep learning or AI systems
- Hands-on experience optimizing inference for large-scale models
- Proficiency in Python and frameworks such as PyTorch
- Experience with inference tooling (Triton, TensorRT, vLLM, ONNX Runtime)
- Ability to design experiments and communicate results clearly
- Preferred
- deploying inference systems at scale, distributed multi-GPU inference, open-source contributions, peer-reviewed publications, working close to hardware (CUDA, ROCm, profiling tools)
- Conditions
- Contract: not stated
- Salary: not stated
- Hours: not stated
- Location: not stated
- Benefits
- none stated
Role Overview
We are seeking an AI Researcher with deep experience in inference optimization to design, evaluate, and deploy high-performance inference systems for large-scale machine learning models. You will work at the intersection of model architecture, systems engineering, and hardware-aware optimization, improving latency, throughput, and cost efficiency across real-world production environments.
Key Responsibilities
Research and develop techniques to optimize inference performance for large neural networks.
Improve latency, throughput, memory efficiency, and cost per inference.
Design and evaluate model-level optimizations (quantization, pruning, KV-cache optimization, architecture-aware simplifications).
Implement systems-level optimizations (dynamic batching, kernel fusion, multi-GPU inference, prefill vs decode optimization).
Benchmark inference workloads across hardware accelerators.
Collaborate with engineering teams to deploy optimized inference pipelines.
Translate research insights into production-ready improvements.
Required Qualifications
Strong background in machine learning, deep learning, or AI systems.
Hands-on experience optimizing inference for large-scale models.
Proficiency in Python and modern ML frameworks (e.g., PyTorch).
Experience with inference tooling (e.g., Triton, TensorRT, vLLM, ONNX Runtime).
Ability to design experiments and communicate results clearly.
Preferred / Nice-to-Have Qualifications
Experience deploying production inference systems at scale.
Familiarity with distributed and multi-GPU inference.
Experience contributing to open-source ML or inference frameworks.
Authorship or co-authorship of peer-reviewed research papers in machine learning, systems, or related fields.
Experience working close to hardware (CUDA, ROCm, profiling tools).
What Success Looks Like
Measurable gains in latency, throughput, and cost efficiency.
Optimized inference systems running reliably in production.
Research ideas successfully translated into deployable systems.
Clear benchmarks and documentation that inform product decisions.
Relevant Research Areas (Bonus)
Long-context inference optimization
Speculative decoding
KV-cache compression and paging
Efficient decoding strategies
Hardware-aware inference design
Originally posted on Himalayas
How to apply
Prepare your application
A cover letter and a short pitch for this job, written from your profile, and what to learn next.
Sign in and create your profile from your CV. It is private: we share it with no one.
Something wrong or unlawful in this ad? Report it
Similar jobs
- AI Researcher — Training OptimizationFeatherless AI
- AI Researcher — AI Architecture ResearchFeatherless AI
- Machine Learning Engineer — Inference OptimizationFeatherless AI
- AI Researcher — DistillationFeatherless AI
- Machine Learning Engineer — AI Architecture ResearchFeatherless AI
- AI Researcher – Multilingual DataFeatherless AI
Salary compared ⓘ
83 jobs · Systems analysts · remote
see the best paid →Training for this job
- Developing Generative AI Applications on AWSRumosonline · daytime · 14 h · 1420 € · starts 01/02/2027Asked for in this ad: AI / machine learning
- AI-3003: Build a natural language processing solution with Azure AI ServicesGalileuonline · daytime · 7 h · 560 € + IVA · starts 24/11/2026Asked for in this ad: AI / machine learning
- Curso de Consultoria e Integração de IAIronhackonline · weekends · daytime · evenings · 7500 € · starts 30/11/2026Asked for in this ad: AI / machine learningPay once employed: “Oferecemos o Income Share Agreement (ISA via Bcas) e opções de pagamentos flexíveis em prestações.” (source)
Languages AI
Published on (2)
- Himalayas seen 17 Nov
- Featherless AI seen 17 Nov – 21 Nov
First seen on 17 Nov, 00:20 · last seen on 21 Nov, 22:32