Associate Engineer - Edge AI

Overview

Help build and sustain the Rust-based platform that manages AI application lifecycles across a heterogeneous fleet of edge hardware, working on constrained compute, cross-architecture builds, OTA updates and production-grade observability.

What you'll do

• Implement and test components of the edge packaging and runtime system, a containerless / OCI-based approach to shipping AI systems to heterogeneous devices
• Contribute to the on-device orchestration platform and help support OTA update and lifecycle management for fielded devices
• Measure and improve inference and resource usage on constrained CPU/GPU/NPU hardware
• Work on cross-compilation and CI/CD pipelines for reproducible, secure multi-architecture builds
• Help integrate the device fleet with the cloud control plane and backend services (REST/gRPC, OpenAPI, MQTT)
• Reproduce, diagnose, and fix defects on real hardware, and turn what you learn into tests
• Use agentic AI coding tools daily for implementation, refactoring, review, and debugging
• Take part in the team's AI-assisted engineering practice: working patterns, guardrails, and what stays human-owned
• Keep the codebase and its documentation in a state that people can work in effectively

What you'll need

• Degree in Computer Science, Machine Learning, or a related field (or equivalent practical experience)
• 1 to 3 years of professional software engineering experience
• Working proficiency in Rust or Python, and willingness to learn the other
• Hands-on experience using agentic AI tools in the software development workflow, including AI coding assistants and agents for implementation, refactoring, and review, and an emerging point of view on their limits
• Comfortable on Linux and with Git-based workflows
• Experience with embedded Linux
• Systematic debugging instincts: you narrow problems down rather than guess
• Clear written communication and the ability to work with a team distributed across the NA, Europe, and India
• Genuine curiosity about the full stack (cloud, edge, and web/backend) and about how the networking stack works

Nice to have

• C/C++ exposure
• Exposure to embedded Linux or systems programming
• ML frameworks or inference runtimes (PyTorch, ONNX, TensorRT, TFLite, OpenVINO) and the realities of running models on device NPU/GPU hardware such as Jetson, Qualcomm, Hailo, or Ambarella
• GenAI/LLM tooling or RAG pipelines
• Multi-arch builds
• A major cloud provider (AWS, GCP, Azure)
• GitLab CI

Details

• Location: Bangalore, India (SEZ)