Senior ML Engineer

Saison International; Bengaluru; On-site; INR 1,500,000 - 2,700,000; Full time

Job summary

Saison International in Bengaluru, India, is seeking an ML Engineer/Senior ML Engineer who enjoys taking ML systems from experimentation to production at scale. You will design real-time and batch pipelines, deploy models for high-throughput inference, and build observability dashboards.

You will collaborate with data scientists and engineering teams, own ML deployments, and apply modern ML frameworks. The role requires 2–5 years of production ML experience, strong Python and SQL skills, and

Qualifications

• 2–5 years of production ML experience, real-time preferred.
• Bachelor's/Master's/PhD in STEM from a top-tier institution.
• Strong fundamentals in ML, neural networks, and deep learning.

Responsibilities

• Design high-throughput feature pipelines for real-time and batch processing.
• Deploy and optimize ML models for production inference workloads.
• Build end-to-end ML observability with tracing and dashboards.
• Own integrations for ML-powered data products and real-time decisions.
• Define scalable infrastructure for ML deployments.
• Architect ensembles, model chaining, shadow deployments, champion-challenger patterns.
• Work with diverse datasets to develop impactful ML solutions.
• Apply modern AI/ML frameworks to business problems.

Skills

Python

SQL

Distributed systems

MLOps

Real-time inference

TensorFlow Serving

Education

Bachelor's in STEM

Master's in STEM

PhD in STEM

Tools

Databricks

MLflow

Kubeflow

Docker

PyTorch

scikit-learn

TensorFlow

Spark

Job description

We are looking for an ML Engineer/Senior ML Engineer who enjoys taking machine learning systems beyond experimentation and into high-scale, production environments. You will work closely with data scientists and engineering teams to build real-time ML infrastructure, high-throughput inference systems, feature pipelines, model serving platforms, and production observability. This is an engineering-heavy ML role for someone who enjoys solving problems at the intersection of machine learning, distributed systems, platform engineering, and MLOps.

Responsibilities:

• Design and build high-throughput, low-latency real-time and batch feature computation pipelines.
• Partner with data scientists to deploy, profile, optimize, and scale complex ML models for production inference workloads.
• Build end-to-end ML observability, including tracing, monitoring, alerting, and production dashboards.
• Own technical integrations for ML-powered data products and real-time decisioning systems.
• Define and optimize infrastructure for scalable ML deployments.
• Architect systems supporting advanced model deployment patterns such as ensembles, model chaining, shadow deployments, and champion-challenger frameworks.
• Work across internal and external datasets to build impactful ML solutions.
• Apply modern AI/ML frameworks to solve critical business problems.

Requirements:

• 2-5 years of hands-on experience deploying machine learning models in production, preferably real-time environments.
• Bachelor's / Master's / PhD in a STEM discipline from a top-tier institution.
• Strong fundamentals in machine learning, neural networks, and deep learning.
• Strong understanding of distributed systems, real-time computing, and inference-serving architectures.
• Strong programming skills in Python and SQL.
• Exposure to Databricks is highly advantageous.
• Strong software engineering fundamentals and an emphasis on production-quality code.
• Comfortable using modern developer tools, including AI coding assistants such as Claude Code / Codex.

Hands-on exposure to:

• Model Serving: TensorFlow Serving, ONNX.
• Cloud: AWS ecosystem.
• MLOps: MLflow, Kubeflow.
• Containers: Docker.
• ML: PyTorch, scikit-learn.
• Explainability: SHAP, LIME.
• Distributed Processing: Apache Spark.

Strong Plus:

• Experience building ML systems in financial services, fintech, lending, or credit.
• Understanding of model risk management and compliance frameworks.
• Experience operating ML systems where latency, reliability, monitoring, and scale are critical.