Applications and AI Engineer İş İlanı

We are looking for a highly capable engineer who can contribute across embedded development, real-time processing, and system integration. The role requires both depth in programming and algorithms and breadth across hardware and software domains — you will work on everything from firmware on microcontrollers to high-level applications that handle video, communication, control, and the interpretation of complex sensor data. This is a role with real ownership rather than a specification to implement. Much of the work starts as a question nobody has answered yet — why a measurement drifts, whether a feature is achievable inside the latency budget, what the camera is really doing at the edge of its range — and ends as something that flies. If you are equally happy in a datasheet, in an estimator, and on a field-test bench, you will find plenty of room here. About SiFly Aviation

At SiFly, we’re building a new category of aircraft: vertical-takeoff, long-endurance drones that deliver helicopter-level performance at drone economics. After thousands of flight tests and years of engineering, our NDAA-compliant platform flies more than 2 hours in hover or 3 hours in forward flight on a single charge — matching the capability of traditional helicopters at a fraction of their cost and operational burden. We merge aerial robotics, perception, and onboard intelligence to cut complexity and minimize human intervention, and our unique approach to communications and networking unlocks remote operations from day one. It’s an ambitious mission, and we’re a small team that moves fast. The role

You will build the software between the sensors and the product: firmware on constrained hardware, the signal processing, estimation, and vision that turn raw sensor output into something trustworthy, and the applications and data paths that carry video, telemetry, and control with low latency and predictable behavior. Along the way you will calibrate cameras, fuse sensors that disagree with each other, and chase problems across the hardware, firmware, and software layers until they have an actual cause. You will work closely with the rest of the Applications and AI team, the embedded platform and firmware engineers whose interfaces you build on, the flight-software team, and our hardware engineers in Santa Clara — designing the architecture together, testing in the field, and iterating quickly on what the aircraft actually does rather than what it was supposed to do. What you’ll do

Write real-time embedded Linux software. Design and implement software for real-time systems, ensuring robustness and performance on constrained hardware. Apply signal processing, estimation, and vision. Use techniques from digital signal processing, estimation theory, and computer vision to extract information, improve performance, and enable advanced features. Fuse the sensors. Combine information from multiple sensors to improve reliability and accuracy in dynamic environments — including when they disagree. Integrate complete systems. Connect and coordinate sensors, actuators, and communication interfaces into complete, working systems rather than isolated components. Build the data paths. Create efficient pathways for video, telemetry, and sensor data, with an emphasis on low latency, stability, and clarity of output. Own the camera behaviour. Work with image sensors and their parameters — exposure, shutter speed, ISO, and focal characteristics — and apply calibration methods to achieve consistent, repeatable results. Debug across the whole stack. Investigate and solve issues that arise across the hardware, firmware, and software layers, and drive them to root cause rather than to a workaround. Take ideas from prototype to product. Rapidly validate concepts, then refine them into reliable, maintainable solutions that other engineers can build on. Make results legible. Develop clear ways to present complex measurements and results for debugging, calibration, and system evaluation — so the team can reason about the data, not just look at it. Work in the field. Collaborate closely with the team to design architecture, test on real aircraft, and iterate quickly on what you learn there. Required experience

Embedded and real-time programming. Demonstrated strength in embedded systems programming in C, C++, and Python, and in real-time development on constrained hardware. Algorithms and theory. Solid understanding of digital signal processing, computer vision, and sensor-fusion principles, and the ability to design and optimize algorithms for real-time execution and estimation. Sensor integration. Experience integrating sensors, actuators, and communication modules, including calibration and alignment. System-level debugging. Practical expertise in debugging, profiling, and solving problems that cross component boundaries — where the answer is rarely in the layer where the symptom appeared. Breadth and ownership. Comfort working across disciplines and taking ownership of technical challenges end-to-end, from first investigation through to something maintainable. Advanced English language skills and strong written and verbal communication — able to coordinate clearly across a distributed team in Turkey and Santa Clara. Nice to have

Robotics, drones, or other real-time mechatronic systems · video streaming, networking, or GPU-accelerated computation · deploying systems to field environments and adapting them under real-world conditions · camera calibration workflows, including intrinsic parameters such as focal length, distortion, and alignment, and the tooling around them · multi-camera or stereo rigs and time synchronization across sensors · MAVLink, ROS, or comparable robotics and autopilot interfaces · detect-and-avoid, tracking, or perception pipelines · UAV, automotive, or other safety-relevant embedded experience. What success looks like

Features move from idea to something flying on real aircraft without stalling in the gap between prototype and product. Sensor outputs are trusted: measurements are calibrated, characterized, and understood well enough that the rest of engineering builds on them without hedging. Video, telemetry, and sensor data arrive with latency and stability that are measured and held to, not hoped for. Problems that cross hardware, firmware, and software boundaries get an owner and a root cause rather than being passed around. Calibration and evaluation are repeatable processes with tooling behind them, not one-off efforts that depend on who ran them. The team can see what the system is doing — measurements and results are presented clearly enough to make decisions from. Details Job type: Remote contract-based employment. Location: On-site position in Ankara, Turkey — working closely with our Santa Clara team.