Senior Software Engineer – Cloud & Edge Inference (NVIDIA Jetson) (India)

Senior Software Engineer – Cloud & Edge Inference (NVIDIA Jetson) (India)

05 Aug
|
OURS GLOBAL
|
India

05 Aug

OURS GLOBAL

India

About Company

OURS GLOBAL is a leading offshore IT & ITeS outsourcing company delivering innovative solutions across software development, cloud, SaaS, BI, and IT support services. With global delivery capabilities and a strong focus on scalability, transparency, and performance, we empower businesses across industries to accelerate growth and efficiency through technology.

We are currently hiring a Senior Software Engineer – Cloud & Edge Inference (NVIDIA Jetson) at our Bangalore office. If you are passionate about cloud-edge hybrid architectures, AI inference optimization, and containerized deployments, this is your chance to work on cutting-edge GenAI workloads with global impact.

Job Details

Job Title: Senior Software Engineer – Cloud & Edge Inference (NVIDIA Jetson)

Location: Bangalore [Remote/Hybrid]

Salary: As per Industry Standards

Education: Bachelor’s/Master’s degree in Computer Science, Engineering, or related fields.

Experience: 10+ Years in Software Engineering

Job Summary:

As a Senior Software Engineer – Cloud & Edge Inference (NVIDIA Jetson), you will design and implement a unified Docker-based deployment pipeline for cloud and edge environments. You will optimize real-time inference services for GenAI models (LLMs and beyond) running on NVIDIA Jetson devices, while collaborating with AI/ML teams to enable scalable hybrid deployments. This role combines cloud orchestration expertise with edge performance optimization, making it critical to our AI-driven solutions strategy.

Key Responsibilities:

- Design & implement a Docker-based deployment pipeline for seamless cloud and edge integration.




- Optimize and adapt Python/FastAPI inference services for real-time GenAI performance on edge devices.
- Build & maintain Kubernetes deployments for hybrid workloads (cloud + NVIDIA Jetson).
- Collaborate with AI/ML teams to integrate and deploy inference models to edge environments.
- Troubleshoot, optimize, and stabilize inference workloads under constrained edge hardware conditions.

Skills & Qualifications:

- 10+ years of qualified software engineering experience.
- Strong proficiency in Python (FastAPI experience preferred).
- Proven expertise with Kubernetes and container orchestration at scale.
- Hands-on experience with real-time AI inference on embedded GPUs (NVIDIA Jetson or similar).
- Solid knowledge of performance optimization and resource constraints in edge environments.
- Strong problem-solving ability and team-oriented mindset across AI/ML and infrastructure teams.

Preferred Qualifications:

- Experience with GPU acceleration frameworks (CUDA, TensorRT).
- Familiarity with CI/CD pipelines for containerized deployments.
- Knowledge of network optimization for cloud-to-edge communication.
- Background in distributed systems and scalable architectures.

What We Offer:

- Chance to work on cutting-edge AI inference solutions across cloud and edge.
- Exposure to hybrid cloud architectures with global clients.
- A collaborative and innovation-driven work culture.
- Competitive salary packages aligned with industry standards.
- Continuous learning opportunities in AI, edge computing, and advanced cloud technologies.

Job Application Details:

Candidates fulfilling the above requirements may email their resume to [email protected], walk-in or you can submit your resume online

📌 Senior Software Engineer – Cloud & Edge Inference (NVIDIA Jetson) (India)
🏢 OURS GLOBAL
📍 India

Reply to this offer

Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.

Subscribe to this job alert:

Get the latest job offers by email for: senior software engineer – cloud & edge inference (nvidia jetson) (india) / india

Subscribe to this job alert:

Get the latest job offers by email for: senior software engineer – cloud & edge inference (nvidia jetson) (india) / india