# lijo jacob

lijo jacob is a remote worker on Himalayas, Senior ML Engineer, Research at Blaize, Inc., based in United States.

Source: https://himalayas.app/@lijojacob

```text
Senior Machine Learning Engineer at Blaize, Inc. who deployed Qwen3-VL-30B-A3B across multiple GPUs for video-frame analysis.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | United States |
| Authorized to work in | United States |
| Salary expectations | 163k+ USD |
| Job categories | Machine Learning Engineer, Deep Learning Developer, Computer Vision Engineer, Machine Learning Research Engineer, Embedded Software Engineer, Software Engineer |
| Skills | Machine Learning, Computer Vision, Deep Learning, Object Detection, Model Deployment, Inference Optimization, Edge AI, Model Distillation, Incremental Learning, Image Segmentation, Vision Language Models, Multi GPU Inference, MLOps, Digital Signal Processing, Keyword Spotting |
| LinkedIn | https://linkedin.com/in/lijo-jacob-71502121 |

## About

```text
At Blaize, Inc., I built a YOLOv8 aerial object detection system for video analytics on Blaize edge hardware. Error analysis and a small-object detection head raised mAP50:95 from 64.4 to 66.2.

I also distilled a YOLOv5x detector into a YOLOv5m student, cutting parameters by about 75% and compute by about 4x while keeping accuracy within 1 to 2 mAP points. For 2K video, I built an adaptive tiled inference pipeline using SAHI to balance detection accuracy and latency.

For video-frame analysis, I evaluated LLM serving options and deployed Qwen3-VL-30B-A3B across multiple GPUs with an image-query API. I also rebuilt the detection and segmentation auto-labeling pipeline on Grounding DINO and SAM, reducing manual labeling effort by 20%.

At Mythic, Inc., I adapted object detection models to analog in-memory compute hardware using noise-aware training, quantization-aware training, and pruning. Earlier at Ignitarium Technology Pvt. Ltd., I deployed digit recognition on a Renesas MCU and optimized a footwear defect detection pipeline with TensorRT.
```

## Experience

### Senior ML Engineer, Research

Blaize, Inc.. Oct 2022 - Sep 2026

```text
Built and deployed computer vision pipelines on edge hardware, including YOLOv8 aerial detection and adaptive tiled inference. Deployed a 30B vision-language model with vLLM and developed tools to accelerate prototyping and auto-labeling.
```

Skills: YOLOv8, YOLO-V5, Sahi, VLLM, Qwen3VL, GroundingDINO, SAM, Prometheus, Grafana, Python, C++, Computer-Vision, Edge-AI, Incremental-Learning, Drift-Monitoring

### Model Development Engineer

Mythic, Inc.. Feb 2021 - Jul 2022

```text
Adapted object detection models to analog in-memory compute hardware using noise-aware training and quantization. Re-architected post-processing for improved throughput and designed test suites to reduce regression failures.
```

Skills: PyTorch, DDP, RayTune, Weights-Biases, Tensorboard, S3, C++, Python, Quantization, Pruning, Noise-Awareness-Training, Object-Detection, COCO

### Senior Engineer

Ignitarium Technology Pvt. Ltd.. Mar 2019 - Mar 2022

```text
Deployed models on resource-constrained hardware, including digit recognition on an MCU and keyword spotting on a microcontroller. Optimized defect detection with TensorRT and built a container ID recognition pipeline.
```

Skills: TensorRT, C, C++, Python, MCUs, Raspberry-Pi, Keyword-Spotting, MFCC-(Feature-Extraction), Digital-Signal-Processing, Object-Detection, Edge-AI

### AI Engineer

Cognub Decision Solutions. Apr 2018 - Mar 2019

```text
Developed an image-to-text extraction engine for insurance invoices, combining classical image processing with deep learning.
```

Skills: Image-Processing, Deep-Learning, OCR, Python

### ML Engineer

Pixuate. Dec 2016 - Mar 2018

```text
Built an inventory management system using deep learning to analyze shelf space and track demand-to-supply gaps.
```

Skills: Deep-Learning, Computer-Vision, Python

## Education

### MG University

M.E., Signal Processing

```text
Master of Engineering in Signal Processing from MG University, India, completed in 2015.
```

### CUSAT

B.E., Electronics and Communication

```text
Bachelor of Engineering in Electronics and Communication from CUSAT, India, completed in 2011.
```

## Tech stack

- Python
- C++
- C
- PyTorch
- Grafana
- Prometheus
- Git
- Docker
- Weights & Biases
- vLLM
- AWS

To contact lijo, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Tianchang Liu](https://himalayas.app/@ismaeltc): Senior AIOps Manager, Tredence
- [Amir Salazar](https://himalayas.app/@amirsalazar): Senior Machine Learning Engineer, Uber
- [Emilio Amtonio](https://himalayas.app/@emilioamtonio4): Lead AI Developer, BlitzMobileApps
- [Andrew Long](https://himalayas.app/@andrewlong): AI Engineer, Freelance
- [Ali Anderson](https://himalayas.app/@alianderson): Senior Machine Learning Engineer, DeepVision AI
- [Abhishek Gaur](https://himalayas.app/@abhishekgaur2): Senior Machine Learning Engineer, Adobe
- [Chris Ku](https://himalayas.app/@chrisku): Senior Machine Learning Engineer, Raspberry AI
- [Amit Yadav](https://himalayas.app/@amityadav9): Open Source Developer, Kiwix Foundation
- [Tarmily Wen](https://himalayas.app/@tarmilywen): Senior AI/ML Engineer, Walmart
- [Sachin Lodhi](https://himalayas.app/@sachinlodhi): Lead Computer Vision Engineer & Data Scientist, IntuigenceAI
