Who Am I ?
About Me
Computer Science graduate with a strong foundation in AI research and hands-on machine learning. My work centers on computer vision, including segmentation, pose estimation, 3D mesh reconstruction, and object detection. I have built biomechanical analysis pipelines with OpenSim, and have fine-tuned and trained diffusion models, generating synthetic datasets as part of product development. My experience covers production optimization and deployment of models using TorchCompile, TFLite, and ONNX. I also enjoy research and contributed to academic work during my B.Tech, alongside delivering trained and fine-tuned models for production use in real projects.
Experience
Software Developer – AI/ML
Valere Labs, Indore
- Leading development of AI systems for sports analytics, integrating deep learning with biomechanical simulation workflows.
- Engineered a multi-stage 3D human-motion reconstruction pipeline that lifted 2D keypoints to 3D poses, fused temporal cues using SLAM-style optimization, and generated SMPL-X meshes for downstream analysis in OpenSim.
- Designed and optimized the video-processing pipeline, reducing end-to-end latency by 55% through parallelization, batching, and caching.
- Fine-tuned and deployed YOLO-based detection and tracking models on edge/mobile; achieved major speedups using ONNX Runtime, TensorRT, and custom pre/post-processing kernels.
- Performed model optimization via quantization, pruning, and operator-level optimizations, improving inference throughput by nearly 50% across devices.
- Contributed to internal GenAI systems, integrating LLMs, RAG, and agent-based automation for multimodal query workflows.
AI Trainee – AI Research
Monotype Imaging Inc., Noida
- Developed and trained a custom diffusion model for in-image text editing, enabling localized text modification while preserving font characteristics, layout structure, and visual coherence.
- Conducted applied research on Rectified Flow and ControlNet to enhance controllability, structural consistency, and text fidelity in generated outputs.
- Fine-tuned large-scale models (SDXL, Flux) on proprietary font datasets, significantly improving stylistic consistency.
- Created high-quality synthetic datasets and fine-tuned segmentation models to support font-conditioned diffusion pipelines.
- Accelerated inference by 65% through optimization of generation stages, scheduler parameters, and post-processing.
ML Engineer
Humanli.ai, Jaipur
- Built a custom CNN for pneumonia detection from chest X-rays, achieving 95% accuracy and advancing to clinical trial validation.
- Designed and deployed an LLM-based analytics workflow using LLaMA-2, RAG, and multi-agent orchestration.
- Led dataset preparation, cleaning, augmentation, and model validation for medical imaging pipelines.
Education
-
Baba Banda Singh Bahadur Engineering College
Bachelor of Technology: Computer Science and Engineering
July 2019 - June 2023- CGPA: 8.90/10
My Skills
Programming Languages
Data Science And Machine Learning
IOT
Others
Research Publications
1. Image Forgery Detection: A Survey Of Recent Approaches
Proceedings of 4 National Research Scholars MEET-2023 Evolving Trends and Challenges in
Multidisciplinary Research
March 17, 2023, pp 357-360
Author: Amneet Kaur, Basav Bamrah, Prof. Jaspreet Kaur CSE dept Baba Banda Singh
Bahadur Engineering College
2. Sign Language Recognition Using Convolutional Neural Networks
Sign Language Recognition using Convolutional Neural Networks, Vol 9 No 1&2 (2022): Journal
of Advanced Research in Electronics Engineering and Technology
Author: Basav Bamrah, Prof. Jaspreet Kaur CSE dept. Baba Banda Singh Bahadur
Engineering
College
My Projects
Let's Connect
I'm currently looking for new opportunities. Whether you have a question or just want to say hi, feel free to drop me an email or connect on LinkedIn!
Or click to copy my email:
bamrah.basav@gmail.com