Job Description

Nisum is a leading global digital commerce firm headquartered in California, with services spanning digital strategy and transformation, insights and analytics, blockchain, business agility, and custom software development. Founded in 2000 with the customer-centric motto "Building Success Together," Nisum has grown to over 1,800 professionals across the United States, Chile, Colombia, India, Pakistan, and Canada. A preferred advisor to leading Fortune 500 brands, Nisum enables clients to achieve direct business growth by building the advanced technology they need to reach end customers in today’s world, with immersive and seamless experiences across digital and physical channels.

What You'll Do

This is an ideal position for a highly motivated and technically skilled professional who thrives in a fast-paced, innovation-driven environment. The Deployment Engineer will be responsible for packaging, deploying, and maintaining machine learning models and services in production environments. This role requires a deep understanding of model serving frameworks, CI/CD practices, and container orchestration tools to ensure scalable and reliable ML infrastructure.

Model Packaging & Serving

• Package machine learning models for deployment using frameworks such as MLflow and TorchServe.
• Develop model APIs using FastAPI, Flask, or Streamlit to serve predictions at scale.
  
  

CI/CD & Automation

• Design and maintain CI/CD pipelines for ML using tools like GitHub Actions, Jenkins, GitLab CI, or Argo Workflows.
• Automate testing, deployment, and monitoring of models in production environments.
  
  

Containerization & Orchestration

• Use Docker to containerize applications and ensure consistent environments across dev, staging, and prod.
• Deploy and scale services using Kubernetes, with a focus on model inference scalability and reliability.
  
  

Monitoring, Logging & Integration

• Set up logging and monitoring systems to track model performance, uptime, and failures.
• Integrate deployed models with client-facing applications and APIs for seamless data flow and prediction delivery.
  
  

What You Know

• Strong experience in model deployment using FastAPI, Flask, Streamlit, and model serving frameworks like MLflow or TorchServe.
• Deep knowledge of CI/CD tools and pipelines tailored for ML workflows.
• Hands-on expertise with Docker and Kubernetes, particularly for autoscaling and managing inference workloads.
• Proficiency in setting up observability for ML models (monitoring, logging, alerting).
• Experience integrating deployed models with production systems and APIs.
  
  

Additional Requirements

• Strong understanding of ML lifecycle management in enterprise environments.
• Proactive problem-solver with an automation-first mindset.
• Ability to collaborate effectively with data scientists, DevOps, and software engineering teams.
• Comfortable working in agile and globally distributed teams.
  
  

Education

• Bachelor’s or Master’s degree in Computer Science, Data Engineering, or a related field.
  
  

Benefits

In addition to competitive salaries and benefits packages, Nisum offers its employees some unique and fun extras:

• Health Benefits: Comprehensive health coverage, including in-patient, out-patient care, and life insurance.
• Work-Life Balance: Flexible paid time off for medical leave, pilgrimage, family planning, and personal time.
• Incentives & Rewards: Financial rewards, interest-free loans, extra salary, car financing, and savings programs.
• Development & Training: Structured training, study sponsorships, international trips, and appreciation programs.
• Corporate Appliances: Essential work tools, including a laptop, internet device, and accessories.
• Office Facilities: Gym, gaming room, free lunches, and a vibrant work environment.