{"id":1285134,"url":"https://alion.io/job/technosoft-engineering-projects-limited-slam-computer-vision-engineer","title":"SLAM & Computer Vision Engineer","company":{"id":3810694,"name":"Technosoft Engineering Projects Limited","domain":"technosofteng.com","url":"https://alion.io/company/technosoft-engineering-projects-limited","size_band":"501-1000","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":"senior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Mumbai, India","Pune, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":20000,"max_usd":42000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":29},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon EC2","optional":false},{"name":"Amazon SageMaker","optional":false},{"name":"Apache Kafka","optional":false},{"name":"AWS","optional":false},{"name":"AWS Lambda","optional":false},{"name":"Computer Vision","optional":false},{"name":"Fine-tuning","optional":false},{"name":"ONNX Runtime","optional":false},{"name":"Quantization","optional":false},{"name":"RabbitMQ","optional":false},{"name":"Segment Anything","optional":false},{"name":"TensorRT","optional":false},{"name":"Transfer Learning","optional":false},{"name":"YOLO","optional":false},{"name":"A/B Testing","optional":true},{"name":"Albumentations","optional":true},{"name":"C","optional":true},{"name":"CI/CD","optional":true},{"name":"ClearML","optional":true},{"name":"CUDA","optional":true},{"name":"CUDA Toolkit","optional":true},{"name":"FFmpeg","optional":true},{"name":"Human-in-the-Loop","optional":true},{"name":"Keras","optional":true},{"name":"Machine Learning","optional":true},{"name":"MLFlow","optional":true},{"name":"NumPy","optional":true},{"name":"OpenCV","optional":true},{"name":"Pandas","optional":true},{"name":"Pillow","optional":true},{"name":"Python","optional":true},{"name":"PyTorch","optional":true},{"name":"SHAP","optional":true},{"name":"TensorFlow","optional":true},{"name":"Weights & Biases","optional":true}],"status":"live","first_seen_at":"2026-08-17T11:44:57Z","employer_posted_date":null,"last_verified_at":"2026-08-17T11:44:57Z","board_verified":false,"closed_at":null,"days_open":44,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":44},"description":"ABOUT US : \n\nTechnosoft Engineering Solutions is building an AI-powered visual intelligence platform for the Indian construction industry. We bridge the gap between what is planned (BIM models, 2D drawings) and what is built on site, using real-time visual intelligence and spatial computing.\n\nTHE ROLE : \n\nWe are looking for a Computer Vision & AI Engineer to design and build scalable vision AI pipelines that process large volumes & variety. You will implement end-to-end AI pipeline : video preprocessing, model architecture (YOLO, SAM, segmentation models), training on construction datasets, inference optimization, and MLOps for continuous improvement.\n\nWHAT WE ARE LOOKING FOR : \n\nComputer Vision & Deep Learning (Core Requirement) : \n\n- Hands-on experience building object detection and segmentation models in production : YOLO, SAM (Segment Anything Model), or similar architectures\n\n- Strong fundamentals in CNNs, vision transformers, attention mechanisms, and multi-scale feature extraction\n\n- Practical experience with semantic segmentation and instance segmentation for complex, cluttered environments\n\n- Model training on custom datasets : data annotation pipelines, class imbalance handling, augmentation strategies\n\n- Transfer learning and fine-tuning : adapting pre-trained models to domain-specific tasks\n\n- Experience with 2D - to - 3D or video-to-BIM alignment is a strong plus\n\nLarge-Scale Video Processing & Inference Optimization (Core Requirement) : \n\n- Experience building scalable video processing pipelines handling TBs of data per month\n\n- Batch processing architecture : distributed inference across GPU clusters, queueing systems (RabbitMQ, Kafka, etc.), chunked video processing\n\n- Model optimization for production : quantization, pruning, ONNX Runtime, TensorRT\n\n- Frame sampling strategies for efficient video analysis (every Nth frame, keyframe extraction, motion-based sampling)\n\n- Experience with cloud-based GPU inference (AWS EC2 P3/P4, Lambda, SageMaker) and cost optimization\n\nTraining Data & Domain-Specific Model Development (Core Requirement) : \n\n- Experience training models on noisy, real-world data : handling dust, shadows, occlusions, varying lighting conditions, motion blur\n\n- Building custom datasets : defining labeling guidelines, managing annotation teams, quality control\n\n- Multi-class classification with 50+ element classes across various construction segments\n\n- Defect detection modelling - cracks, rebar exposure, missing components, misalignments, incomplete work is strong plus\n\nHybrid 2D/3D AI & BIM Integration (Good to have) : \n\n- Experience working with BIM models (IFC files) or CAD drawings as reference for AI analysis\n\n- Spatial reasoning : matching detected elements in video frames to BIM element locations using coordinate transformations\n\n- Zone-based analysis : segmenting floor plans into zones, aggregating detection results per zone/floor\n\n- Progress quantification : computing completion percentages from detection outputs (e.g., \"Floor 7 Finishes 40% complete\")\n\nMLOps & Production AI Systems (Good to have) : \n\n- Model versioning, experiment tracking (MLflow, Weights & Biases, ClearML)\n\n- CI/CD for ML : automated retraining pipelines, A/B testing new models in production, monitoring model drift\n\n- Production monitoring : precision/recall tracking per class, confidence score distributions, detection latency, inference cost per video\n\n- Human-in-the-loop (HITL) workflows : flagging low-confidence predictions for manual review, feedback loops for continuous improvement\n\n- Experience with model explainability (Grad-CAM, SHAP) for debugging and trust\n\nProgramming Languages : \n\n- Python - expert level (PyTorch, TensorFlow, OpenCV, NumPy, Pandas)\n\n- Deep learning frameworks : PyTorch (preferred) or TensorFlow/Keras\n\n- Computer vision libraries : OpenCV, Albumentations, Pillow\n\n- GPU programming : CUDA basics, understanding GPU memory management\n\n- Familiar with video codecs (H.264, H.265), FFmpeg for video manipulation\n\nQUALIFICATIONS : \n\n- 5 - 10 years of professional software engineering experience\n\n- 3 - 5 years building production computer vision / deep learning system\nSkills\nVisual SLAM, Computer Vision, Python, Artificial Intelligence, Machine Learning, Deep Learning, GPU, OpenCV, Video Analytics, MLOps, BIM","description_format":"text","description_chars":4314,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Robotic Software & Control Systems"],"lifecycle":[{"event":"open","at":"2026-09-26T04:00:00Z"}],"liveness":{"score":25,"band":"fade","label":"Fading","p_open":0.6,"p_active":0.744,"p_room":0.55,"age_days":43,"expected_fill_days":41,"reasons":["seen:43","win:tail"],"computed_at":"2026-09-30T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/technosoft-engineering-projects-limited-slam-computer-vision-engineer","json_url":"https://alion.io/job/technosoft-engineering-projects-limited-slam-computer-vision-engineer.json","meta":{"generated_at":"2026-10-01T01:35:44Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":995,"day_limit":5000,"remaining_today":4005,"minute_limit":60,"resets_at":"2026-10-02T00:00:00Z"}}}