Multimodal Sensing and Fusion Engineer at Helsing

Berlin; London; MunichFull-timeHardware EngineeringPosted about 2 months ago

About the Role

<h2>Who we are</h2> <div> Helsing is a defence AI company. Our mission is to protect our democracies. We aim to achieve technological leadership, so that open societies can continue to make sovereign decisions and control their ethical standards.  As democracies, we believe we have a special responsibility to be thoughtful about the development and deployment of powerful technologies like AI. We take this responsibility seriously.  We are an ambitious and committed team of engineers, AI specialists and customer-facing programme managers. We are looking for mission-driven people to join our European teams – and apply their skills to solve the most complex and impactful problems. We embrace an open and transparent culture that welcomes healthy debates on the use of technology in defence, its benefits, and its ethical implications.  </div> <h2>The role</h2> <div> Helsing builds software and AI that makes existing defence hardware up to ten times more capable. The sensing stack is where that capability begins. Without precise, synchronised, calibrated sensor data, the AI has nothing to work with.  As Multimodal Sensing and Fusion Engineer, you will own that stack end to end. You will architect the multimodal perception front-end that combines electro-optical and long-wave infrared cameras, radar, LiDAR, and inertial sensing into a single, coherent input to Helsing's AI. You will translate mission requirements into concrete specifications for sensor selection, placement, synchronisation, and calibration, and you will define the safety concepts that ensure the system degrades gracefully and fails safe in the field.  This is not a prototyping role. The systems you design go into operational environments. The quality of the data you deliver directly affects the decisions Helsing's AI supports in the field. You will sit at the intersection of hardware engineers, electrical engineers, and AI and computer-vision researchers, working out of Munich, Berlin or London.  </div> <h2>The day-to-day</h2> <ul> <li data-leveltext="" data-font="Symbol" data-listid="5" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="1" data-aria-level="1">Define the multimodal sensing architecture: select and integrate EO and LWIR cameras, radar, LiDAR, and IMUs, aligning requirements with the AI team to optimise algorithm performance and balance trade-offs across size, weight, power, cost, and robustness. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="5" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="2" data-aria-level="1">Own sensor synchronisation: design and implement time synchronisation across heterogeneous sensors using PTP/gPTP, PPS, and hardware triggers such as Hsync and Vsync, so all modalities share a common, precise time base. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="5" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="3" data-aria-level="1">Own sensor calibration: develop intrinsic, extrinsic, spatial, and temporal calibration procedures, including online and continuous recalibration, across cameras, radar, and IMU. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="5" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="4" data-aria-level="1">Define safety concepts: derive failure modes, fault detection, isolation, and recovery concepts for the sensing subsystem, drawing on both defence mission-safety thinking and automotive functional-safety practice (ISO 26262, SOTIF). </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="5" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="5" data-aria-level="1">Drive system design and architecture: analyse the interplay of hardware, software, and algorithm architectures, and define the interfaces and data pipelines from sensor to AI. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="5" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="6" data-aria-level="1">Bring hardware to life: spend hands-on time in the lab bringing up prototypes, testing performance under varying conditions, and supporting integration into the software stack. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="5" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="7" data-aria-level="1">Tune data quality: analyse application-specific sensing performance and adjust designs and low-level algorithms to maximise the value sensor data provides to downstream AI applications. </li> </ul> <h2 id="You’ll-do-great-if-you….3" data-renderer-start-pos="15247">You should apply if you</h2> <ul> <li data-leveltext="" data-font="Symbol" data-listid="6" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="1" data-aria-level="1">A Ph.D. or M.Sc. in Electrical Engineering, Computer Engineering, Applied Physics, Robotics, or a related field, or equivalent professional experience. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="6" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="2" data-aria-level="1">A professional track record building multimodal sensing or sensor-fusion systems combining at least two of: cameras (EO and/or LWIR), radar, LiDAR, and IMU. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="6" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="3" data-aria-level="1">Demonstrated understanding of system-level synchronisation, including PTP/gPTP, PPS, and hardware triggers such as Hsync and Vsync. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="6" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="4" data-aria-level="1">Mastery of sensor calibration, intrinsic and extrinsic, spatial and temporal, including strategies for maintaining calibration across a multi-sensor rig over its operational lifetime. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="6" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="5" data-aria-level="1">The ability to derive safety concepts for a sensing or perception subsystem, from a defence or mission-critical background, an automotive functional-safety background (ISO 26262, SOTIF), or both. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="6" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="6" data-aria-level="1">Strong systems design instincts, comfortable reasoning about the interplay of hardware, software, and algorithms. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="6" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="7" data-aria-level="1">Proficiency in C/C++ or Rust for low-level firmware development and hardware-software interface debugging, plus Python. </li> </ul> Note: We operate in an industry where women, as well as other minority groups, are systematically under-represented. We encourage you to apply even if you don’t meet all the listed qualifications; ability and impact cannot be summarised in a few bullet points. <h2>Nice to Have</h2> <ul> <li data-leveltext="" data-font="Symbol" data-listid="7" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="1" data-aria-level="1">Depth in one or more of the following sensor modalities: thermal imaging (LWIR design, calibration, and programming), FMCW radar signal processing (detection, clustering, and tracking), or LiDAR and point-cloud processing including cross-calibration with cameras and radar. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="7" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="2" data-aria-level="1">IMU and inertial navigation expertise, including GNSS/INS integration, bias and error modelling, and sensor alignment. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="7" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="3" data-aria-level="1">Sensor-fusion estimation experience: Kalman/EKF/UKF, particle filters, factor graphs, multi-object tracking, and data association. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="7" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="4" data-aria-level="1">Low-level hardware experience: FPGA development using Verilog, SystemVerilog, or VHDL, Linux kernel driver development, or experience with high-bandwidth sensor interfaces such as MIPI CSI-2 or LVDS. </li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="7" data-list-defn-props="{"335552541":1,"335559683":0,"335559684":-2,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="5" data-aria-level="1">A background in automotive, robotics, or aerospace sensor fusion, covering ADAS, AUTOSAR, ROS, or ISO 26262 and SOTIF, and familiarity with how sensor data feeds downstream computer-vision or AI pipelines. </li> </ul> <h2>Join Helsing and work with world-leading experts in their fields </h2> <ul> <li> Helsing’s work is important. You’ll be directly contributing to the protection of democratic countries while balancing both ethical and geopolitical concerns </li> <li> The work is unique. We operate in a domain that has highly unusual technical requirements and constraints, and where robustness, safety, and ethical considerations are vital. You will face unique Engineering and AI challenges that make a meaningful impact in the world </li> <li> Our work frequently takes us right up to the state of the art in technical innovation, be it reinforcement learning, distributed systems, generative AI, or deployment infrastructure. The defence industry is entering the most exciting phase of the technological development curve. Advances in our field of world are not incremental: Helsing is part of, and often leading, historic leaps forward </li> <li> In our domain, success is a matter of order-of-magnitude improvements and novel capabilities. This means we take bets, aim high, and focus on big opportunities. Despite being a relatively young company, Helsing has already been selected for multiple significant government contracts </li> <li> We actively encourage healthy, proactive, and diverse debate internally about what we do and how we choose to do it. Teams and individual engineers are trusted (and encouraged) to practise responsible autonomy and critical thinking, and to focus on outcomes, not conformity. At Helsing you will have a say in how we (and you!) work, the opportunity to engage on what does and doesn’t work, and to take ownership of aspects of our culture that you care deeply about </li> </ul> <h2 id="What-we-offer" data-renderer-start-pos="3238">What we offer</h2> <ul> <li> Competitive salary and VSOP options </li> <li> Relocation support: up to €2,500 and 4 weeks temporary accommodation </li> <li> Learning: €500/£450 yearly allowance </li> <li> Health & wellness: gym membership and mental health support (Nilo.health) </li> <li> Social: regular company events and monthly social allowances </li> <li> Enhanced parental leave: 22 weeks fully paid for primary caregivers & 6 weeks for secondary caregivers </li> <li> Family support: 5 days of paid family emergency leave, 100% remote work option during pregnancy and phased return to work </li> <li> A hands-on onboarding program (affectionately labelled “Infraduction”), in which you will be building tooling and applications to be used across the company. This is your opportunity to learn our tech stack, explore the company, and learn how we get things done - all whilst working with other engineering teams from day one  </li> </ul>   Helsing is an equal opportunities employer. We are committed to equal employment opportunity regardless of race, religion, sexual orientation, age, marital status, disability or gender identity. Please do not submit personal data revealing racial or ethnic origin, political opinions, religious or philosophical beliefs, trade union membership, data concerning your health, or data concerning your sexual orientation.<div class="content-conclusion"><div> </div> <div>Helsing's Candidate Privacy and Confidentiality Regime can be found <a href="https://helsing.ai/candidate-privacy-and-confidentiality-regime/" target="_blank">here</a>. </div> <div> </div> <div> </div></div>

About the Role

Related Roles