Sign up to access all features of our service.
  • Job search
  • Favorites
  • Create a CV
    New
  • Salaries
  • Subscriptions

Machine Learning Engineer - GPU Performance & Low-Latency Inference

Fintal Partners

Job Description

We’re partnering with a leading global trading firm to hire a Machine Learning Engineer to make ML models run as fast as possible. You’ll work close to the hardware, squeezing latency out of real-time inference and speeding up training, in an environment where microseconds matter.

What you’ll do

  • Build and optimize low-latency inference pipelines that deliver real-time predictions in production
  • Profile and optimize ML workloads at the device level: memory, compute, kernels and compilers
  • Write and tune custom GPU code (CUDA, Triton or equivalent) where libraries fall short
  • Apply and validate low-precision techniques (FP8/INT8, quantization), knowing which optimizations stay bit-exact,
  • Optimize batching, KV caching and serving paths for latency-critical workloads.
  • Extend the internals of PyTorch and inference frameworks to raise performance on specific workloads

What you’ll bring

  • 3+ years in machine learning, focused on inference or GPU performance
  • Hands-on experience optimizing ML at the GPU level: CUDA, Triton, C++, TensorRT or similar
  • Experience with profiling tools (Nsight, torch.profiler) and reasoning about memory bandwidth, latency and throughput
  • A strong grasp of modern ML architectures, attention in particular, and how they map onto hardware
  • Production-quality Python (C++ a strong plus), with testing discipline and ownership of the systems you ship
  • A habit of measuring before optimizing, and the judgment to know when to build versus buy

Nice to have

  • Experience building real-time, low-latency prediction systems in high-performance environments
  • Experience with numerics: mixed precision, quantization and correctness at scale
  • Contributions to open-source projects such as PyTorch, vLLM, Triton or FlashAttention

No trading experience is required. What matters is deep, hands-on performance engineering and a drive to make things faster.

Vacancy posted 3 days ago
Similar jobs that could be interesting for youBased on the Machine Learning Engineer - GPU Performance & Low-Latency Inference in Chicago, IL vacancy
  •  ...alike.Klover's engineering team powers...  ...security, and performance, and that integrate...  ...transparent, low-fee financial...  ...a Senior Machine Learning Engineer to own...  ...building low-latency online model serving...  ...computing and GPU-accelerated...  ...distributed training/inference), including... 
    Performance
    Work at office
    Immediate start
    1 day per week

    Attain Data

    Chicago, IL
    5 days ago
  •  ..., Cloud, and Software Engineering. Our expertise in AI solution...  ...are seeking a Senior Machine Learning Engineer with...  ...teams to build robust, low-latency ML systems that scale...  ...model drift detection, performance monitoring, and self-healing inference pipelines in high-reliability... 
    Performance
    Full time
    Contract work
    For contractors
    3 days per week

    Xenon7

    Chicago, IL
    27 days ago
  • $165k - $225k

     ...its clients a Senior Machine Learning Engineer - this is a fully remote...  ...evaluate algorithm performance, validate research...  ...ready systems meeting latency and throughput requirements...  ...Experience with GPU acceleration and optimization...  .../ONNX export, and inference serving frameworks... 
    Performance
    Remote work
    Worldwide

    Career Renew

    Chicago, IL
    27 days ago
  • $180k - $240k

     ...one of its clients a Senior Machine Learning Engineer - this is a fully remote...  ...latest research into high-performing systems and models that can...  ...) Familiarity with low-latency production ML systems (Mandatory...  ...problems — low latency inference, hallucination reduction,... 
    Performance
    Remote work
    Flexible hours

    Career Renew

    Chicago, IL
    27 days ago
  •  ...quantitative trading firm is seeking a Machine Learning Hardware Engineer to help deploy machine...  ...the technical direction of ML inference in a demanding, latency-sensitive trading environment....  ...identify measurable improvements in performance. What you’ll bring:... 
    Performance

    Fintal Partners

    Chicago, IL
    11 days ago
  •  ...Title: Low Latency Network Engineer Location: New York or Chicago (4x per week onsite) Salary: Up to 250k base + bonus ($500K TOTAL COMP...  ...leading technical role in shaping the global networks behind a performance-critical financial technology business. You’ll influence... 
    Performance

    Hamilton Barnes ??

    Chicago, IL
    a month ago
  •  ...Head of Core C++ Low Latency Development About the Company Successful proprietary trading...  ...the development of robust, high-performance trading systems. Responsibilities for the...  ...valued. A degree in computer science, engineering, or a related field is typically required... 
    Performance

    Confidential

    Chicago, IL
    2 days ago
  •  ...looking for an MLOps Engineer to deploy, scale,...  ...DevOps, Data Engineering, Machine Learning, or Software...  ...model serving (Triton Inference Server, TorchServe, KServe...  ...managing/provisioning GPU compute resources....  ...experimentation to reliable, high-performance production deployment... 
    Performance
    Work at office
    Remote work
    Relocation
    Visa sponsorship
    Work visa
    Flexible hours
    3 days per week

    AgileEngine

    Chicago, IL
    18 days ago
  •  ...retraining. Deploy and manage machine learning models in production...  ...with Data Scientists and ML Engineers to optimize model deployment...  ...tools. Monitoring model performance, latency, availability, and resource...  .... Experience with GPU-based workloads and ML model... 
    Performance
    H1b
    Local area

    ETHEREUM TECHNOLOGIES LLC

    Chicago, IL
    5 days ago
  • $90 - $120 per hour

     ...Dorsey . Position: MLOps Engineer, LLM Systems (Serving, GPU Kernels, Profiling) Type:...  ...across GPU kernels , performance profiling , debugging , and inference serving . Write accurate, well...  ...and serving throughput and latency trade-offs. Collaborate with... 
    Performance
    Contract work
    Summer work
    Remote work

    Mercor

    Chicago, IL
    8 days ago
  • $62k - $100k

     ...Description About the Role As an AI Engineering team member, you will be instrumental in...  ...a comprehensive total rewards package. Learn more about what working at Crowe can...  ...their goals with tax, advisory, risk and performance services. Crowe is recognized by many organizations... 
    Performance
    Full time
    Local area
    Worldwide

    Crowe

    Chicago, IL
    4 days ago
  • $179.4k - $204.7k

    Machine Learning Engineer 4 Do you love building and pioneering in the AI and technology space? Do you enjoy solving complex business problems...  ...and Data Engineering. In this role, you'll be expected to perform many ML engineering activities, including one or more of the... 
    Performance
    Full time
    Part time
    H1b
    Local area

    Capital One

    Chicago, IL
    56 minutes ago
  • $135k - $162k

     ...TitleSenior AI/ML Engineering ManagerJob ID1088...  ..., coaching, performance management, and career...  ...requires it: inference and serving systems...  ...Science, Engineering, Machine Learning, Data Science,...  ...tuning, latency budgeting, and awareness...  ...model endpoints, GPU / CPU workloads)... 
    Performance
    Full time
    Work at office
    Local area
    Immediate start

    Bain & Company

    Chicago, IL
    3 days ago
  •  ...REQ8336We are seeking highly skilled C++ engineers to join our Systematic technology team, focused on building modern low latency, high availability research, and trading infrastructure...  ...and infrastructure, with a focus on performance, reliability, and scalability. Market... 
    Performance

    Balyasny Asset Management

    Chicago, IL
    5 days ago
  •  ...forward when it matters most. Learn more about CCC at .The RoleAs a Senior Machine Learning Engineer, you'll own models and evaluations...  ...and measuring how they perform Hands-on experience with both...  ...us through Nice to haveCausal inference, survival analysis, or calibration... 
    Performance
    Full time

    CCC Information Services

    Chicago, IL
    2 days ago
  • Machine Learning EngineerThe RoleUST is searching for a Machine Learning Engineer to design, build, and deploy ML models that drive insights...  ...for model training and inference. · Train, tune, and evaluate...  ...deployed models for performance, data drift, and degradation... 
    Performance
    Full time
    Temporary work
    Part time
    Work at office
    Local area
    Remote work
    Flexible hours

    UST Global

    Chicago, IL
    2 days ago
  • $135.1k - $231.6k

     ...we’re looking for a Staff Machine Learning Engineer on the Data Science Team....  ...model training, ensuring low-latency and high-availability at enterprise...  ...education records, and inferences drawn from your PI. We...  ...for our purposes, including performing services and operations... 
    Full time

    Integral Ad Science

    Chicago, IL
    3 days ago
  • $150k - $300k

     ...operate at a level most engineers never encounter? We...  ...Engineer to build real-time, GPU-accelerated...  ...typical front-end role. The performance bar here is closer to game...  ...usage, and frame latency under extremely heavy,...  ...graphics pipelines, and low-level rendering techniques... 
    Performance
    Immediate start

    NJF Global Holdings Ltd

    Chicago, IL
    a month ago
  •  ...seeks an AI/ML & MLOps Engineer to lead the architecture...  ...governance of production machine learning capabilities supporting...  ...deployment; monitor model performance and drift; and control updates...  ...drift, concept drift, inference quality, latency, availability, errors,... 
    Performance
    Contract work
    For contractors
    Local area
    Remote work

    Decisionpoint Corporation

    Chicago, IL
    4 days ago
  • $175k - $275k

     ...hypotheses and measure model performance before production...  ..., statistical, and machine-learning models; prototype...  ....Apply statistical inference, optimization,...  ...Mathematics, Financial Engineering, Computational Mathematics...  ...that trade on low latency scale at the milisecond... 
    Performance
    Permanent employment
    Full time
    Remote work

    IMC Inc

    Chicago, IL
    2 days ago
  • $117.61k - $153.15k

     ...improve product/system performance, quality, data...  ...maintenance. Applies deep learning technologies to give computers...  ...key components of the Machine Learning Platform...  ...data scientists, data engineers, and IT teams to design...  ...Experience with GPU acceleration (e.g. CUDA... 
    Performance
    Hourly pay

    United Airlines

    Chicago, IL
    2 days ago
  • $180k - $200k

     ...Senior Machine Learning Engineer - Fraud Detection Remote, USA $180,000 – 200,000 base salary + annual bonus + equity THE COMPANY...  ...learning models that improve fraud detection accuracy and system performance. Lead experimentation initiatives, including model... 
    Performance
    Remote work
    Flexible hours

    Harnham

    Chicago, IL
    5 days ago
  • $179.4k - $204.7k

    Machine Learning Engineer 4 (Manager, IC) Do you love building and pioneering in the AI and technology space? Do you enjoy solving complex business...  ...and Data Engineering. In this role, you'll be expected to perform many ML engineering activities, including one or more of... 
    Performance
    Full time
    Part time
    H1b
    Local area

    Capital One

    Chicago, IL
    56 minutes ago
  • $62k - $100k

     ...About the Role· We work on medium-term machine learning projects (1-6 months) with a high...  ...language (C/C++, Go, etc) is a plus Software engineering experience. You enjoy software...  ...their goals with tax, advisory, risk and performance services. Crowe is recognized by many... 
    Performance
    Full time
    Local area
    Worldwide
    Shift work

    Crowe

    Chicago, IL
    4 days ago
  • $200k - $300k

     ...infrastructure that allows our high-capacity, low-latency trading and data research environments...  .... We are looking for a Senior Network Engineer with experience designing and managing large environments to fulfill the high-performance and availability requirements of a... 
    Performance
    Work at office
    Local area
    Immediate start
    Worldwide

    Hudson River Trading

    Chicago, IL
    5 days ago
  •  ...We're looking for a **Machine Learning Engineer** to help build and improve AI-powered products. You'll work with large datasets, train and evaluate...  ...analyze datasets for model training. * Improve model performance through experimentation and testing. * Deploy and... 
    Performance
    Remote work
    Flexible hours

    Spotter AI

    Chicago, IL
    a month ago
  • $200k - $225k

    We are deploying machine learning directly onto custom hardware - and we...  ...researchers and experienced engineers from any background. Trading...  ...treating hardware constraints (latency budgets, resource limits,...  ...implement, verify, and deploy ML inference solutions from proof-of-... 
    Permanent employment
    Full time

    IMC

    Chicago, IL
    1 day ago
  • $205k - $265k

     ...Most US-based positions can also be performed remotely (any exceptions will be...  ...of lives. We are seeking a Staff Machine Learning Engineer / Data Scientist to serve as a technical...  ...learning research into high-throughput, low-latency production systems. This is a high... 
    Full time
    Remote work
    Flexible hours

    ZipRecruiter

    Chicago, IL
    15 days ago
  • $120k - $180k

     ...headquartered in Chicago, IL. Learn more at [coinflow.cash...  ...We're hiring an MLOps Engineer to own the platform...  ...of real money, so latency, reliability, and...  ...Build and operate the inference layer that scores transactions...  ...testing, compare performance on our data, and give... 
    Performance
    Full time
    Worldwide

    Coinflow

    Chicago, IL
    18 days ago
  • $180k - $225k

     ...forward when it matters most. Learn more about CCC at . The Role As a Senior Machine Learning Engineer, you'll own models and...  ...production and measuring how they perform Hands-on experience with both...  ...Nice to have   Causal inference, survival analysis, or calibration... 
    Performance
    Remote job

    EvolutionIQ

    Chicago, IL
    19 hours ago

Do you want to receive more vacancies?

Subscribe and receive similar vacancies to Machine Learning Engineer - GPU Performance & Low-Latency Inference. Be the first to apply!