Genies · 1 day ago
Machine Learning Engineer: ML Infra and Model Optimization
Los Angeles, California, United States
Full-time
Hybrid
Mid, Senior Level
$215K/yr - $275K/yrGenies is an avatar technology company powering the next era of interactive digital identity through AI companions. They are looking for a ML Infra and Model Optimization Engineer to join their R&D team, focusing on building and maintaining production-grade ML infrastructure and optimizing model inference at scale.
AppsAugmented RealityBlockchainGenerative AIInternetMedia and EntertainmentMobile AppsSocial Network
Responsibilities
Design, build, and maintain production-grade ML infrastructure for image and 3D generative models
Develop and own backend services and APIs that support model inference at scale (high concurrency, low latency, high reliability)
Deploy, monitor, and operate ML models on cloud and large-scale platforms (e.g., SageMaker, Kubernetes, Ray Serve, custom GPU services)
Optimize inference pipelines using model acceleration techniques such as:
Quantization, pruning, mixed precision
ONNX / TensorRT / torch.compile
Partner with ML researchers to productionize diffusion models, transformer-based models, and 3D generation systems
Implement evaluation, logging, monitoring, and alerting to ensure system stability and performance
Improve end-to-end system efficiency across data loading, inference, post-processing, and storage
Support rapid experimentation while maintaining production safety and scalability
Qualification
Required
Strong experience building backend and infrastructure systems in production environments
Proficiency in Python and experience designing APIs/services (e.g., FastAPI, Flask, gRPC)
Hands-on experience deploying and operating ML models at scale, including: GPU-based inference services, concurrency handling and request batching, latency and throughput optimization
Experience with cloud platforms and ML deployment stacks, such as: AWS (SageMaker, EC2, EKS), GCP, or similar, Docker, containers, CI/CD pipelines
Solid understanding of systems performance, debugging, and reliability engineering
Experience supporting real user traffic, not just offline research workflows
Preferred
Experience with generative models, especially: diffusion models, transformer-based architectures, multimodal image / 3D pipelines
Familiarity with 3D generation or computer graphics pipelines (e.g., meshes, textures, multi-view data)
Hands-on experience with model optimization and acceleration, such as: quantization, pruning, distillation, ONNX Runtime, TensorRT, FSDP, DeepSpeed
Experience with distributed systems or scalable inference frameworks (Ray, Triton, TorchServe)
Background in machine learning fundamentals (training, evaluation, model behavior), even if not research-focused
Benefits
Comprehensive health insurance for you and your family (Anthem + Kaiser Options Available), Dental and Vision Insurance
Flexible paid time off, sick time, and paid company holidays, in addition to paid parental leave, bereavement leave, and jury duty leave for full-time employees
Health & wellness support through programs such as monthly wellness reimbursement
Working in a brand new, bright, open-environment and fun office space - there’s even a slide!
Choice of MacBook or windows laptop
Company
Genies
Genies is an Avatar Technology Company creating an avatar experiences for their users.
Founded in 2011
51-200 employees
H1B Sponsorship
Genies has a track record of offering H1B sponsorships. Please note that this does not
guarantee sponsorship for this specific role. Below presents additional info for your
reference. (Data Powered by US Department of Labor)
Distribution of Different Job Fields Receiving Sponsorship
Represents job field similar to this job
Trends of Total Sponsorships
2025 (11)
2024 (6)
2023 (7)
2022 (2)
2021 (2)
2020 (2)
Funding
Current Stage
Growth StageTotal Funding
$266.96MKey Investors
Silver LakeRobert IgerBond
2022-04-12Series C· $150M
2022-03-14Angel
2021-05-03Series B· $65M
Leadership Team
Akash Nigam
CEO & Founder
Jake Adams
COO & Co-founder
Recent News
2025-12-31
2025-12-31
Company data provided by crunchbase