Key Responsibilities

- Prototype and benchmark real time ML inference pipelines (CUDA, TensorRT, ONNX Runtime).

- Develop GStreamer/WebRTC modules for video ingestion & real time visualization.

- Implement shared memory IPC and compare with socket based transfers.

- Build distributed messaging layers using ZeroMQ (pub sub, request reply).

- Profile system performance: latency, CPU GPU memory transfers, multi core contention.

What We’re Looking For

- Education: BE/ME/B.Tech in CS/IT or related discipline.

- Core Skills: Strong Modern C++ (RAII, smart pointers, memory layout) and/or Rust fundamentals.

- Systems Knowledge: OS concepts (threads vs. processes, synchronization, CPU cache hierarchy).

- Workplace: Proficiency in Linux CLI, build tools (CMake,



Make, Cargo, GCC/Clang)

Bonus Skills (Nice to Have)

- Exposure to NVIDIA CUDA, TensorRT, PyTorch C++ API.

- Familiarity with ZeroMQ patterns (Majordomo, broker architectures).

- Projects involving GStreamer, WebRTC, OpenCV, or distributed messaging.

Why Join Us?

- Work on real time ML systems with direct mentorship from senior professinals

- Opportunity to convert to a full time PPO.

- Be part of a fast growing deep tech company in Pune.

Pay: From ₹7,500.00 per month

Work Location: In person

📌 Systems, Distributed Computing & Real Time ML intern (Baner)
🏢 AI4M Technology Private
📍 Baner