Edge AI Model Compiler & Deployment Engineer

At CraftifAI, we're building PipeGen under CraftifAI Orbit: an AI-native, multi-agent development platform that helps engineering teams build, optimize, and deploy production-ready perception pipelines for edge devices.

PipeGen brings together a collaborative set of specialized AI agents that automate different stages of the deployment lifecycle—from model analysis and optimization to compilation, validation, and deployment across GPUs, NPUs, DSPs, and embedded edge platforms.

By combining Edge AI, model optimization, compiler technologies, AI agents, and deployment automation, we're building the next generation of AI-powered developer tools that simplify how AI applications move from trained models to production.

As an Edge AI Deployment & Model Compiler Engineer, you'll contribute to the Model Compiler capabilities within PipeGen, focusing on model optimization, compilation, validation, and deployment across diverse edge hardware platforms.

You'll build and enhance a collaborative set of specialized AI sub-agents that automate different stages of the model deployment lifecycle. These modular, plug-and-play components integrate seamlessly with PipeGen's AI orchestration platform, enabling intelligent collaboration with other specialized agents across the perception pipeline.

This role is ideal for engineers passionate about Edge AI, model optimization, deployment automation, and intelligent developer tools.

• Design and develop AI-powered workflows for model analysis, optimization, compilation, deployment validation, and runtime diagnostics.
• Build and enhance specialized AI sub-agents responsible for different stages of the model deployment lifecycle.
• Develop model ingestion and analysis pipelines for ONNX and related model formats, including graph inspection, compatibility analysis, and deployment readiness.
• Build model optimization workflows involving graph optimization, operator fusion, quantization, pruning, sparsity, precision optimization, and hardware-aware inference techniques.
• Develop intelligent deployment workflows that select the most appropriate compiler frameworks, inference runtimes, and optimization strategies across GPUs, NPUs, DSPs, and embedded edge platforms.
• Develop automated validation and benchmarking workflows to verify deployment correctness, runtime behavior, inference accuracy, latency, throughput, and overall model performance.
• Debug compiler logs, runtime failures, and deployment issues to improve deployment reliability and developer productivity.
• Collaborate with AI researchers, compiler engineers, platform engineers, and product teams to continuously improve PipeGen's deployment capabilities.

• 1–3 years of experience in Edge AI, AI model deployment, ML infrastructure, model optimization, compiler engineering, or related software engineering roles.
• Experience deploying AI models on GPUs, embedded systems, or other resource-constrained edge hardware.
• Experience developing TensorRT plugins, CUDA kernels, or custom operators for hardware-specific optimizations.
• Experience deploying AI models on NVIDIA Jetson or other NVIDIA embedded GPU platforms. Familiarity with Qualcomm AI Engine (QNN), NPUs, DSPs, or other heterogeneous edge AI accelerators is a plus..
• Strong understanding of graph optimization, operator fusion, precision optimization (FP32, FP16, INT8), quantization, pruning, sparsity, dynamic shapes, and memory-performance trade-offs.
• Experience debugging compiler logs, model compatibility issues, runtime failures, and deployment bottlenecks.
• Strong Python programming skills for automation, tooling, validation, and internal platform development.

• Experience building developer tools, SDKs, ML deployment platforms, or automation frameworks.
• Exposure to AI agents, agent orchestration, robotics, ROS, sensor fusion, or multimodal AI systems is a plus.
• Familiarity with Computer Vision or perception models. Interest in AI agents, LLMs, RAG, or AI-assisted developer tools is a plus.

At CraftifAI, you'll help build PipeGen, an AI-native platform that's transforming how perception pipelines are developed and deployed for Edge AI applications.

You'll work at the intersection of Edge AI, model optimization, compiler technologies, AI deployment, and AI-powered automation, solving real-world deployment challenges while contributing to a collaborative ecosystem of specialized AI agents.

If you're passionate about building the next generation of intelligent Edge AI deployment platforms and developer tools, we'd love to hear from you.