Senior Computer Vision Engineer

We need to output HTML fragment with sections: About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Only include sections that have real specific content. The posting includes: About CFD Research (company description) maybe not needed as section? The instruction: use

for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we need to map content to those headings. The posting includes description of role: "CFD Research is looking for a Senior Computer Vision Engineer who will design, develop, and optimize advanced computer vision and multi‑sensor fusion algorithms supporting GEOINT‑mission workflows..." That's about the role. Then responsibilities: list of duties: "Develop and implement deep learning computer vision models, with a focus on sensor fusion and target tracking", "Collaborate with multidisciplinary teams to design, develop, test, and deploy technical solutions in Python or C++", "Utilize GPU programming, including CUDA or RAPIDs, to optimize the performance of computer vision applications", "Contribute to the architecture and implementation of novel single and multi-sensor detection and tracking and fusion of targets". Those are responsibilities. Requirements: Basic Qualifications list: 6+ years experience, 2+ years deep learning, active TS/SCI clearance, US citizen, Bachelor's degree, experience implementing pipelines in Python/C++, knowledge of GPU-accelerated development, knowledge of classical tracking methods, knowledge of PINNs, ability to design/test/optimize algorithms for operational performance in constrained computing environments. Qualifications: Desired Qualifications list: experience with GPU-accelerated deep learning, synthetic data, advanced estimation/tracking/fusion techniques, geospatial data formats, MLOps, microservice architectures, edge integration, familiarity with transformer-based vision architectures beyond DINO/CLIP/SAM, experience with cloud ML platforms, Master's or Ph.D. Skills: maybe combine knowledge areas? Could list skills like Python, C++, CUDA, RAPIDS, TensorRT, etc. But we can put skills under Skills section derived from qualifications. However we must not invent content; we can extract explicit skill mentions: Python, C++, CUDA, RAPIDS, TensorRT, Kalman filters, extended filters, Physics-Informed Neural Networks, etc. But we need to ensure we only include content that is present. The posting mentions many specific skills; we can list them under Skills. Benefits: The posting includes benefits description: competitive salaries, employer matching 401(k), ESOP, insurance package (medical, vision, dental), company paid leave, compensation time, parental leave, long-term and short-term disability, accidental death and dismemberment, life insurance, performance appraisals twice a year, annual pay increases based on corporate goals, personal development, performance, outstanding achievements, group and individual bonuses for exceptional performance. Also note part-time/temporary may receive partial benefits. So we have benefits content. Pay: The posting does not give specific salary numbers or range. It mentions "competitive salaries" but no numbers. According to instruction: never create Pay/Schedule/Benefits sections unless the posting actually states them. For Pay, we need actual numbers or explicit statement like "salary range $X-$Y". Since only "competitive salaries" is vague, we should not include Pay section. Similarly Schedule: location says "This role is based in the Dayton, OH area, and is 100% onsite." That's schedule? It's location and onsite. Not schedule like full-time/part-time/hours. It mentions Full-Time, permanent employee-owners. So we could infer schedule is full-time. But we should not create Schedule unless posting actually states them. It does say "Full-Time, permanent employee-owners". That indicates schedule is full-time. Might be acceptable to include Schedule section with that detail. However instruction: "never create Pay/Schedule/Benefits sections unless the posting actually states them." It does state Full-Time. So we can include Schedule with that detail. But we also have location info; maybe we could include location under About the role? But we can keep location in Schedule or maybe not needed. We'll include Schedule with "Full-time: Full‑time, 100% onsite in Dayton, OH". That's derived from posting. Now we need to output HTML fragment only, no /. Use

for each section heading, then content:

for prose,

• for lists. We must not repeat job title as heading. Not include Job ID etc. We need to preserve all substantive information; do not invent or summarize away detail. So we need to include all details from posting. Let's extract sections: About the role: Should include description of role and maybe company overview? The instruction says use

  for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we can have About the role containing the paragraph describing the role and maybe company overview? The company overview is not about the role but about CFD Research. Might be better to put company overview under About the role? The heading "About the role" suggests role description. The company overview could be considered part of About the role? Might be okay to include it there as context. But we must not invent headings; we can include company overview in About the role as prose. Responsibilities: list of duties. Requirements: Basic Qualifications. Qualifications: Desired Qualifications. Skills: maybe we can extract explicit skill mentions from both Basic and Desired. But we risk duplication. However we can still list them under Skills as bullet points; but we must not invent. The posting includes many skill mentions: Python, C++, CUDA, RAPIDS, TensorRT, Kalman filters, extended filters, Physics-Informed Neural Networks (PINNs), Physics-constrained loss functions, GPU-accelerated development, deep learning, transformer-based or self-supervised architectures, model pipelines, synthetic data, kinematic target models, scenario simulation tools, joint multi-sensor registration, Bayesian fusion, particle filters, deep multi-object tracking pipelines, geospatial data formats, sensor phenomenology, remote-sensing exploitation workflows, MLOps, Docker, Kubernetes, ONNX Runtime, Triton Inference Server, microservice architectures, distributed systems, edge/embedded/latency-constrained environments, transformer-based vision architectures beyond DINO/CLIP/SAM (ViT variants, self-supervised multi-modal encoders), cloud ML platforms (AWS GovCloud, Azure ML, on-prem GPU clusters). Also mention of TS/SCI clearance, US citizenship, Bachelor's degree, Master's/Ph.D. We could put those under Skills. But we also have Requirements and Qualifications sections that already contain many of those as bullet points. To avoid duplication, we could keep Requirements and Qualifications as they are, and Skills could be omitted if no explicit skill list separate. However instruction: "Prefer a few substantive sections over many thin ones." So we could combine Requirements and Qualifications into one? But they ask to use those headings if content exists. We have both Basic and Desired qualifications, so we can have Requirements (Basic) and Qualifications (Desired). Skills could be derived but might be thin. Might be better to omit Skills section if not explicitly listed as a separate "Skills" bullet list. The posting does not have a separate "Skills" heading; it's embedded in qualifications. So we should not create a Skills section unless we have explicit skill list. Safer to omit Skills. Thus sections: About the role, Responsibilities, Requirements (Basic Qualifications), Qualifications (Desired Qualifications), Benefits, Schedule (Full-time, onsite). No Pay. Now we need to ensure we include all substantive information: company overview, role description, responsibilities list, basic qualifications list, desired qualifications list, benefits list, schedule info. We must not include boilerplate like EEO, scam warning, navigation, cookie, legal. The posting ends with "CFD Research is an EO employer - Veterans/Disabled and other protected categories". That's boilerplate; we should remove. Also remove "Learn more at www.cfd-research.com" maybe considered boilerplate? It's a link; but it's substantive? It's a reference; maybe we can keep as part of About the role? It's not essential but could be considered boilerplate. Safer to remove. Now craft HTML. Structure:

  About the role

  CFD Research, founded in 1987, delivers innovative technology solutions in Aerospace & Defense, Biomedical & Life Sciences, Intelligence & Sensing, and Energy & Materials. The company has earned multiple national awards for application and commercialization of innovative component/system technology prototypes, multi-physics simulation software, multi-disciplinary analyses, and expert support services. Headquartered in Huntsville, Alabama with laboratory facilities there, plus offices and labs in Dayton, Ohio; prototyping test and evaluation facilities in Hollywood, Alabama; and office facilities in Fort Walton Beach, Florida. CFD Research is ISO9001:AS9100D registered, CMMI Level II for Services, a 100% ESOP (employee-owned) company recognized in Inc. Magazine's Inc5000 as a top growing company for four of the last five years. CFD Research is seeking a Senior Computer Vision Engineer to design, develop, and optimize advanced computer vision and multi‑sensor fusion algorithms supporting GEOINT‑mission workflows. The candidate will participate in developing deep learning models, real‑time tracking systems, and GPU‑accelerated pipelines deployed in operational environments, shaping next‑generation tools that integrate imaging physics, ML‑based behavior inference, and multi‑sensor fusion.

  But we need to avoid too much detail? We must preserve all substantive information. The company overview includes many details: inception year, industries, awards, facilities, certifications, ESOP, Inc5000. We should keep them. Now Responsibilities:

  Responsibilities

  • Develop and implement deep learning computer vision models, with a focus on sensor fusion and target tracking
  • Collaborate with multidisciplinary teams to design, develop, test, and deploy technical solutions in Python or C++
  • Utilize GPU programming, including CUDA or RAPIDs, to optimize the performance of computer vision applications
  • Contribute to the architecture and implementation of novel single and multi-sensor detection and tracking and fusion of targets
  Now Requirements (Basic Qualifications):

  Requirements

  • 6+ years of experience developing computer vision algorithms for detection, tracking, or multi‑sensor fusion in remote sensing or GEOINT‑relevant environments
  • 2+ years of experience applying deep learning to computer vision problems using transformer‑based or self‑supervised architectures
  • Must possess an ACTIVE TS/SCI security clearance to be considered
  • Experience implementing model pipelines in Python or C++, including training, evaluation, and deployment workflows
  • Knowledge of GPU‑accelerated development using CUDA, RAPIDS, or other GPU programming frameworks
  • Knowledge of classical tracking or estimation methods (such as Kalman or extended filters) to support real‑time algorithm development
  • Knowledge of Physics-Informed Neural Networks (PINNs), Physics-constrained loss functions
  • Ability to design, test, and optimize algorithms for operational performance in constrained computing environments (i.e., multi‑GPU servers or cloud)
  • Bachelor’s degree in a related STEM field
  • Must be a U.S. Citizen
  Now Qualifications (Desired Qualifications):

  Qualifications

  • Experience with GPU‑accelerated deep learning, including CUDA kernel development, TensorRT optimization, RAPIDS, or distributed multi‑GPU training
  • Experience developing synthetic data, kinematic target models, or scenario simulation tools to support algorithm training or evaluation
  • Experience with advanced