About the Team
The Seeker Team builds the eyes and the targeting logic of our weapon system: a low-cost, mass-producible, multimodal missile seeker that leans on commercial supply chains where they outperform, and vertically integrates wherever possible. On a modern missile, the seeker is 40 to 60% of unit cost and often drives overly long delivery cycles; accordingly, the seeker team is at the tip of the spear for delivering capability to our customers and value to the taxpayer.
Seeker design has exactly two real constraints: physics and mission. Nothing else is a show-stopper, only an obstacle to overcome. We are a small, deeply technical team that drives capability through ingenuity and bias for action and ships hardware that flies. This is a wear-many-hats environment where you must be comfortable "building the airplane in flight" and stepping well outside your comfort zone; a narrowly scoped role with clean handoffs is not what this team offers.
This is an AI-native team. Through fluent use of cutting-edge agentic coding tools, one engineer here consistently out-delivers a much larger conventional team. You will have opinions about where these tools help and where they do not, provide governance input, and build out an AI-centric workflow from day one.
About the Role
You will contribute to the production of perception and estimation algorithms at the core of our seeker: detection, tracking, classification, and aimpoint localization on infrared (IR) imagery and fused sensor measurements, against targets that fight back. As part of the Seeker Team, you will research, implement, optimize, and validate algorithms in these areas, including modern AI and machine learning (ML) methods where they earn their place. Runtime efficiency is a hard constraint: everything you build must run within a strict latency budget on embedded flight-compute hardware. You will work closely with the broader Seeker Team to carry your algorithms from first prototype into flight.
What You'll Do
-
Design and implement object detection algorithms for mid-wave infrared (MWIR) and long-wave infrared (LWIR) imagery, robust to clutter, domain shift, and countermeasures.
-
Develop multi-object tracking and state estimation: filtering, data association, and line-of-sight estimates for missile guidance.
-
Implement track lifecycle management: initialization, maintenance, confirmation, and termination under real sensor conditions.
-
Develop segmentation, classification, and discrimination algorithms that separate targets from decoys, debris, and background.
-
Develop aimpoint localization and the associated image-processing methods that support terminal accuracy.
-
Contribute to perception-related sensor fusion, combining IR and X-band radar measurements into a consistent track picture.
-
Implement, optimize, and validate your algorithms for real-time flight: measured latency, covariance and confidence you can defend, and performance proven in simulation, in hardware-in-the-loop testing, and in flight data.
-
Research and prototype advanced AI and ML methods within perception and estimation, and help mature the ones that prove out into the flight pipeline.
Skills We're Hiring For
-
Bachelor of Science (B.S.) in Optical Engineering, Computer Science, Electrical Engineering, Aerospace Engineering, Applied Math, Physics, or a related field; Master of Science (M.S.) or Doctor of Philosophy (Ph.D.) preferred.
-
5 to 7 years of experience in applied computer vision, perception, or estimation on real sensor data.
-
Fluency in state estimation: the Kalman filter family, including nonlinear variants and interacting multiple model (IMM) approaches, applied with judgment.
-
Data association at multi-target scale: joint probabilistic data association (JPDA), multiple hypothesis tracking, or modern equivalents, chosen with judgment.
-
Classical optical image and signal processing as a working toolkit, with emphasis on methods for optical sensors: spatial and temporal filtering, morphology, non-uniformity and fixed-pattern noise handling, and techniques for imagery with a low signal-to-noise ratio (SNR).
-
Statistical rigor as a habit: normalized estimation error squared (NEES) and normalized innovation squared (NIS) consistency testing, covariance validation, and calibrated confidence.
-
3+ years of experience using python to create, alter, and maintain libraries of algorithms within a modern Git & CI/CD framework.
Bonus Points For
-
Rust for real-time implementation and familiarity with embedded CUDA
-
Missile, interceptor, or guided-munition perception or tracking experience.
-
Track-before-detect or other methods for detection and tracking at low SNR.
-
IR or other non-visible-band sensor experience, including synthetic-to-real domain adaptation.
-
TensorRT or comparable edge inference deployment experience.
-
Multi-sensor registration, boresight exploitation, or radar measurement familiarity.
-
Modern machine learning fluency (PyTorch or equivalent): training, evaluating, and shrinking perception models with measured accuracy tradeoffs.
-
Daily use of agentic coding tools (Claude Code or similar) to multiply your output.
Eligibility & Logistics Location: On-site at our Los Angeles, CA HQ; remote work is not available. Monthly weekend travel for test events and supplier engagements. Clearance: A clearance is not required for this position. Must be a U.S. Person.
Equal Opportunity & Export Compliance Furientis is an equal-opportunity employer. To comply with U.S. export control laws, employment is contingent on eligibility to access export-controlled information.