AI/ML/Gen AI Engineer

Ascendion; Bengaluru; On-site; INR 1,800,000 - 3,600,000; Full time

Job summary

Ascendion is seeking a Data Science/Operations Research professional in Bengaluru to develop optimization models and validate inputs, with experience in solvers like CPLEX and OR-Tools. You will ensure data quality, run health checks, and communicate findings to stakeholders.

Responsibilities include scenario analysis, data pipeline monitoring, and mentoring juniors, with cloud experience and strong documentation skills expected.

Qualifications

• 3–8+ years of experience in data science or operations research.
• Hands-on optimization modeling with solvers (CPLEX, OR-Tools).
• Experience with Python for modeling and automation.
• Strong SQL and data validation skills.
• Cloud experience (AWS) preferred.

Responsibilities

• Build and maintain mathematical optimization models — objective functions, constraints, and penalty calibration.
• Encode and validate business rules, contract parameters, and operational constraints into model inputs.
• Execute regression testing and model health checks before and after every production run.
• Conduct scenario and sensitivity analysis with documented trade-offs and business recommendations.
• Validate all input files pre-run — NULL checks, format errors, anomalies, and data readiness sign-off.
• Monitor data pipeline health, audit logs, and ingestion failures across recurring run cycles.
• Perform data quality assessments — missingness, outliers, duplicate records, and consistency checks.
• Validate model outputs and savings calculations — ensuring mathematical accuracy and business defensibility.
• Review compliance and performance tracking — compare actuals vs recommendations and document deviations.
• Review output files for anomalies and formatting issues before stakeholder delivery.
• Support recurring run preparation — scenario setup, input file review, and run orchestration.
• Triage platform issues — classify severity, gather diagnostics, and escalde with clear context.
• Monitor cloud pipeline health — ingestion, compute, and delivery layer checks.
• Maintain run logs, SOPs, runbooks, and knowledge base in structured auditable format.
• Partner with business stakeholders to explain model outputs and recommendations in plain language.
• Mentor junior team members on best practices, coding standards, and documentation discipline.

Skills

Data Science

Operations Research

Python

SQL

Cloud (AWS)

Documentation

Tools

CPLEX

OR-Tools

Dataiku

Airflow

Docker

Kubernetes

FastAPI

PuLP

Job description

Job Responsibilities

• Build and maintain mathematical optimization models — objective functions, constraints, and penalty calibration
• Encode and validate business rules, contract parameters, and operational constraints into model inputs
• Execute regression testing and model health checks before and after every production run
• Conduct scenario and sensitivity analysis with documented trade-offs and business recommendations
• Validate all input files pre-run — NULL checks, format errors, anomalies, and data readiness sign-off
• Monitor data pipeline health, audit logs, and ingestion failures across recurring run cycles
• Perform data quality assessments — missingness, outliers, duplicate records, and consistency checks
• Validate model outputs and savings calculations — ensuring mathematical accuracy and business defensibility
• Review compliance and performance tracking — compare actuals vs recommendations and document deviations
• Review output files for anomalies and formatting issues before stakeholder delivery
• Support recurring run preparation — scenario setup, input file review, and run orchestration
• Triage platform issues — classify severity, gather diagnostics, and escalde with clear context
• Monitor cloud pipeline health — ingestion, compute, and delivery layer checks
• Maintain run logs, SOPs, runbooks, and knowledge base in structured auditable format
• Partner with business stakeholders to explain model outputs and recommendations in plain language
• Mentor junior team members on best practices, coding standards, and documentation discipline

Required Skills

• 3–8+ years experience in Data Science / Operations Research.
• Hands-on experience with optimization solvers — CPLEX and OR-Tools.(Operation Research Tools)
• Python — modeling, data validation, automation scripting, production-quality coding
• SQL — data querying, pipeline monitoring, audit log review
• Cloud platform experience — AWS or equivalent
• Strong documentation and stakeholder communication skills

Preferred Skills

• Pipeline orchestration tools — Dataiku, Airflow, or equivalent
• Containerization — Docker and Kubernetes
• REST API development — FastAPI or equivalent
• Open-source solver experience — PuLP, OR-Tools
• Domain knowledge in logistics, supply chain, or network optimization
• Cloud certification — AWS