Skip to main content
lijo jacobLJ
Looking for a job

lijo jacob

@lijojacob

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

United States
Message

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

Work history, roles, and key accomplishments

Blaize, Inc. logoBI

Senior ML Engineer, Research

Blaize, Inc.

Oct 2022 - Sep 2026 (3 years 11 months)

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.

YOLOv8YOLO V5
Sahi
VLLM
Qwen3VL
GroundingDINO
SAMPrometheusGrafanaPythonC++Computer VisionEdge AI
Incremental Learning
Drift Monitoring
Mythic, Inc. logoMI

Model Development Engineer

Mythic, Inc.

Feb 2021 - Jul 2022 (1 year 5 months)

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.

Ignitarium Technology Pvt. Ltd. logoIL

Senior Engineer

Ignitarium Technology Pvt. Ltd.

Mar 2019 - Mar 2022 (3 years)

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.

CS

AI Engineer

Cognub Decision Solutions

Apr 2018 - Mar 2019 (11 months)

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

PI

ML Engineer

Pixuate

Dec 2016 - Mar 2018 (1 year 3 months)

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

Education

Degrees, certifications, and relevant coursework

MU

MG University

M.E., Signal Processing

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

CU

CUSAT

B.E., Electronics and Communication

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

Tech stack

Software and tools used professionally

Availability

Looking for a job

Location

United States

Authorized to work in

Salary expectations

163k+ USD

Interested in hiring lijo?

You can contact lijo and 600K+ other talented remote workers on Himalayas.

Message lijo

People also viewed

View all talent

Get matched with your dream remote job

Sign up now and join over 1,000,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan