{"id":1225670,"url":"https://alion.io/job/apeaf-founding-computer-vision-edge-ai-engineer-c-cuda-tensorrt","title":"Founding Computer Vision & Edge AI Engineer- C++ / CUDA / TensorRT","company":{"id":3798388,"name":"APEAF","domain":"aatmanirbhar-bharat.org","url":"https://alion.io/company/apeaf","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"junior","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"inferred_payroll_markers","remote_working_hours":null,"hiring_geo_confidence":"inferred","locations":[],"countries":[],"hiring_countries":["IN"],"hiring_countries_total":1,"salary":{"min":1200000,"max":2400000,"currency":"INR","period":"year","gross":true,"usd_annual":25157},"salary_estimate":null,"experience_years_min":2,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"C++","optional":false},{"name":"Computer Vision","optional":false},{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"Digital Twin","optional":false},{"name":"Edge AI","optional":false},{"name":"GitHub","optional":false},{"name":"GStreamer","optional":false},{"name":"Localization","optional":false},{"name":"ONNX","optional":false},{"name":"ONNX Runtime","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"PyTorch C++","optional":false},{"name":"Quantization","optional":false},{"name":"TensorRT","optional":false},{"name":"MediaPipe","optional":true},{"name":"OpenCV","optional":true}],"status":"live","first_seen_at":"2026-09-17T06:45:01Z","employer_posted_date":null,"last_verified_at":"2026-09-17T06:45:01Z","board_verified":false,"closed_at":null,"days_open":31,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":31},"description":"Position Title: Real-Time Computer Vision & Edge AI Engineer (Founding Engineering Team / Core LLD) \nReporting Structure: High-Level AI Architect (Principal ML Scientist, Google) \nDomain: Sub-16ms Edge AI, 3D Pose & Shape Estimation (SMPL-X), TensorRT C++ Inference, Zero-Copy Systems \nPerformance Benchmark: Hard locked 60 FPS (<16.6 ms total frame budget) on dedicated RTX hardware\n\n1. Position Overview & Architecture \nWe are building a proprietary, ultra-low-latency spatial computing platform centered on high-fidelity 100% 3D Digital Twin architecture and real-time human digitization. \nIn this role, you will serve as the Low-Level Design (LLD) Core AI Engineer, working directly alongside a Lead AI Scientist from Google. Your primary mandate is to solve complex surface occlusion and volumetric estimation challenges by building an ultra-fast C++ inference pipeline. This system must accurately regress a subject's true underlying 3D body shape and skeletal pose directly from a live camera feed. You will deploy models that extract parametric data (SMPL-X shape/pose parameters) and bridge these joint rotations seamlessly into our Vulkan graphics engine via shared GPU memory.\nSystem Architecture: \n● Hardware Camera Ingestion: (V4L2 / GStreamer / CUDA) \n↓ Raw RGB Frames (Zero CPU Copy) \n● Edge AI Inference: (TensorRT / ONNX C++ API for 3D Pose Tracking, Kinematic Anchoring, SMPL-X Shape) \n↓ 3D Skeletal Transforms & Shape Parameters \n● Zero-Copy Shared Memory: (CUDA-Vulkan Bridge feeding directly into OpenRigLogic / MetaHuman Engine) \n\n2. Key Responsibilities & Deliverables \nA. Real-Time 3D Pose & Shape Estimation \n● Deploy and optimize state-of-the-art 3D human body reconstruction models (e.g., Shapy, SMPLify-X, CLIFF) to accurately regress the user's underlying skeletal structure and body volume, effectively bypassing unpredictable surface topologies and complex environmental occlusions. \n● Extract mathematically stable shape parameters (β) and pose parameters (θ) to drive the skeletal hierarchy of a high-fidelity digital avatar. \nB. Edge Inference Pipeline (TensorRT) \n● Translate Python-based research models into production-grade C++ inference engines using NVIDIA TensorRT and ONNX Runtime. \n● Implement INT8/FP16 quantization, layer fusion, and custom CUDA plugins to ensure the entire AI inference pass executes within a strict <10 ms budget per frame. \nC. Temporal Smoothing & Anti-Jitter Kinematics\n● Implement highly optimized temporal filters (Kalman filters, One-Euro filters, optical flow tracking) in native C++ to eliminate all high-frequency jitter from the output joint rotations before they reach the graphics engine. \n● Ensure kinematic constraints (e.g., fixed bone lengths) are strictly maintained to prevent the digital asset from stretching or warping dynamically. \nD. Zero-Copy Ingestion & Engine Synchronization \n● Build hardware-accelerated video capture pipelines using V4L2 or GStreamer to ingest raw camera frames directly into GPU memory. \n● Bridge the output coordinate data and transformation matrices to the graphics team using POSIX shared memory and CUDA-Vulkan interop (VK_KHR_external_memory_fd), eliminating CPU staging overhead. \n\n3. Technical Qualifications & Tech Stack \n● Core Programming: Production-level Modern C++ (C++17/20), Python (strictly for model training/validation), and CUDA C/C++. \n● AI & Acceleration Frameworks: NVIDIA TensorRT, ONNX Runtime (C++ API), PyTorch. \n● Computer Vision Libraries: OpenCV (CUDA backend), MediaPipe C++ bindings. \n● Mathematical Foundations: 3D Kinematics, Matrix Transformations, Quaternions/Euler angles, statistical body modeling (SMPL/SMPL-X architecture). \n● Systems Architecture: Low-latency memory management, multi-threading (std::jthread, lock-free queues), SIMD vectorization. \n\n4. Relevant Projects & Demonstrable Experience (Preferred) \n Candidates will be preferred if they present functional codebases, GitHub repositories, or thesis work covering:\n● Real-Time Body Fitting / Pose Estimation: Practical experience deploying 3D human pose or shape reconstruction models on live video feeds. \n● TensorRT / C++ Deployment: Demonstrable experience stripping a PyTorch model out of Python and running it natively in C++ using TensorRT or ONNX, ideally with custom CUDA layers or INT8 calibration. \n● High-Throughput Vision Pipelines: Built a C++ video processing pipeline that aggressively minimizes latency and avoids memory garbage collection pauses. \n● Kinematics & Smoothing: Applied mathematical filters to raw sensor or AI data to produce smooth, mechanically accurate 3D rotations. \n\n5. Compensation & Engagement Structure \n● Compensation: ₹1,50,000 to ₹2,00,000/month \n● Mentorship: Direct architectural guidance, algorithm review, and technical leadership from a Principal ML Scientist at Google. \n● Hardware: Dedicated high-end workstation equipped with discrete NVIDIA RTX hardware.\n\nSkills\nC++, CUDA, TensorRT, Computer Vision, 3D modeling, ONNX","description_format":"text","description_chars":4978,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"India","iso":"IN","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Robotic Software & Control Systems"],"lifecycle":[{"event":"open","at":"2026-09-25T13:06:44Z"}],"visa":[],"liveness":{"score":24,"band":"cold","label":"Long shot","p_open":0.85,"p_active":0.648,"p_room":0.44,"age_days":29,"expected_fill_days":23,"reasons":["seen:29","win:tail","crowd:junior"],"computed_at":"2026-10-17T05:46:00Z"},"pay":{"stated_usd_annual":25157,"is_top_pay":false},"html_url":"https://alion.io/job/apeaf-founding-computer-vision-edge-ai-engineer-c-cuda-tensorrt","json_url":"https://alion.io/job/apeaf-founding-computer-vision-edge-ai-engineer-c-cuda-tensorrt.json","meta":{"generated_at":"2026-10-18T11:00:54Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":16242,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-19T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":3798388},"rest":"https://alion.io/mcp/rest/get_company?id=3798388"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fapeaf-founding-computer-vision-edge-ai-engineer-c-cuda-tensorrt"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fapeaf-founding-computer-vision-edge-ai-engineer-c-cuda-tensorrt"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fapeaf-founding-computer-vision-edge-ai-engineer-c-cuda-tensorrt"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/apeaf-founding-computer-vision-edge-ai-engineer-c-cuda-tensorrt\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fapeaf-founding-computer-vision-edge-ai-engineer-c-cuda-tensorrt"}]}