AI Infrastructure Engineer
Pokee AI · United States
- Hybrid
- Full-time
- $150,000 / year
- United States
Tailored resume — keyword-matched to this role.
Hiring manager — we find who's hiring.
Intro email — drafted to reach them directly.
Job highlights
- Build and optimize AI agent training and inference systems.
- Ensure reliable enterprise-grade AI infrastructure.
- Work with cloud (AWS, GCP) and on-device deployments.
- Collaborate on productionizing novel AI algorithms.
- Join an elite team shaping enterprise AI's future.
About the role
AI Infrastructure Engineer
Pokee AI is seeking an AI Infrastructure Engineer to build and optimize the systems that power their RL-trained AI agents. This role involves creating scalable training pipelines and high-performance inference serving across cloud and on-device deployments, ensuring that research breakthroughs are translated into reliable enterprise infrastructure.
What You’ll Do
- Design, build, and maintain scalable training and inference infrastructure for RL-based AI agent models.
- Optimize model serving for latency, throughput, and cost across cloud (AWS, GCP) and on-premise/on-device environments.
- Develop and manage CI/CD pipelines, experiment tracking, and model versioning systems.
- Implement efficient data pipelines for training data collection, preprocessing, and reward signal computation.
- Collaborate with research scientists to productionize new algorithms and model architectures.
- Ensure infrastructure meets enterprise requirements for reliability, security, and compliance (SOC 2, data residency).
What We’re Looking For
- 3+ years of experience in ML infrastructure, ML platform engineering, or a related systems role.
- Strong proficiency in Python and systems-level languages (Rust, C++, or Go).
- Hands-on experience with ML serving frameworks (vLLM, TensorRT, Triton, ONNX Runtime, or similar).
- Experience with container orchestration (Kubernetes, Docker) and cloud infrastructure (AWS or GCP).
- Solid understanding of GPU computing, distributed systems, and performance profiling.
- Familiarity with ML experiment tracking and pipeline orchestration tools (MLflow, Weights & Biases, Airflow, or similar).
Bonus Points
- Experience with on-device / edge inference optimization (GGUF quantization, TensorRT-LLM, CoreML, QNN).
- Familiarity with on-premise GPU deployments (NVIDIA DGX, Dell PowerEdge, Lenovo ThinkStation).
- Experience supporting RL training loops or online learning systems in production.
- Background in enterprise software with knowledge of security and compliance frameworks.
- Contributions to open-source ML infrastructure projects.
Who You Are
You want to join a small, elite team solving one of the hardest problems in AI—building agents that actually work in the real world. You’ll have direct impact on the product, access to cutting-edge research, and the opportunity to shape the future of enterprise AI from the ground up.
Key skills/competency
- AI Infrastructure Engineering
- Machine Learning Operations (MLOps)
- Python
- Rust
- C++
- Go
- ML Serving Frameworks
- Kubernetes
- Docker
- AWS
- GCP
Skills & topics
- AI Infrastructure Engineer
- Machine Learning
- MLOps
- Python
- Rust
- C++
- Go
- Kubernetes
- Docker
- AWS
- GCP
- Reinforcement Learning
- Inference Serving
- Training Pipelines
- Enterprise AI
How to get hired
- Tailor your resume: Highlight your 3+ years of ML infrastructure experience, Python, and systems-level language skills.
- Showcase relevant projects: Detail your experience with ML serving frameworks, Kubernetes, Docker, and cloud platforms like AWS or GCP.
- Prepare for technical questions: Be ready to discuss GPU computing, distributed systems, performance profiling, and ML experiment tracking tools.
- Demonstrate passion: Emphasize your interest in solving hard AI problems and your desire to impact enterprise AI development.
Technical preparation
Master Python and systems-level languages (Rust, C++, Go).,Gain hands-on experience with ML serving frameworks.,Practice with Kubernetes, Docker, and cloud platforms.,Understand GPU computing and distributed systems.
Behavioral questions
Describe a complex AI infrastructure challenge you solved.,How do you collaborate with research scientists?,Explain your approach to optimizing for cost and performance.,How do you ensure infrastructure meets enterprise requirements?
Frequently asked questions
- What specific ML serving frameworks does Pokee AI use for their AI Infrastructure Engineer role?
- Pokee AI looks for hands-on experience with ML serving frameworks such as vLLM, TensorRT, Triton, ONNX Runtime, or similar technologies for their AI Infrastructure Engineer position.
- What cloud platforms are preferred for the AI Infrastructure Engineer role at Pokee AI?
- For the AI Infrastructure Engineer role, Pokee AI prefers candidates with experience in cloud infrastructure, specifically AWS or GCP.
- Does the AI Infrastructure Engineer role at Pokee AI involve on-device inference optimization?
- Yes, experience with on-device or edge inference optimization, including GGUF quantization, TensorRT-LLM, CoreML, or QNN, is considered a bonus for the AI Infrastructure Engineer position at Pokee AI.
- What programming languages are essential for the AI Infrastructure Engineer at Pokee AI?
- The AI Infrastructure Engineer role requires strong proficiency in Python and systems-level languages like Rust, C++, or Go.
- What kind of experience is required for the AI Infrastructure Engineer position at Pokee AI?
- Candidates for the AI Infrastructure Engineer position at Pokee AI need 3+ years of experience in ML infrastructure, ML platform engineering, or a related systems role.
- What are the responsibilities of an AI Infrastructure Engineer at Pokee AI?
- An AI Infrastructure Engineer at Pokee AI will design, build, and maintain scalable training and inference infrastructure for AI models, optimize model serving, manage CI/CD pipelines, and collaborate with research scientists to productionize algorithms.
- Is the AI Infrastructure Engineer role at Pokee AI remote-friendly?
- Yes, the AI Infrastructure Engineer role at Pokee AI is a remote position, with a preference for candidates in the US or Singapore.