Sign in to see your fit: the skills, experience and location this job asks for, checked against your profile.
Job description
Application & AI Operations Engineer
Experience: 3–6 years, including at least 1 year integrating LLM APIs in production Work Mode: Remote / Hybrid Role Type: Contract Contract Duration: Initially 6 months, extendable based on project requirements. Budget: ₹8–10 LPA, annualised Only Immediate Joiners
Role Overview
We are seeking an Application & AI Operations Engineer to maintain production web applications, AI-enabled learning products, and self-hosted AI platforms.
You will combine application maintenance and release management with AI quality evaluation, security reviews, provider cost control, and user support, working closely with platform engineers to keep services reliable, secure, and current.
Key Responsibilities
Maintain applications built with Node.js, TypeScript, React/Next.js, Python, and PostgreSQL. Fix defects, deliver small enhancements, update dependencies and runtimes, and accommodate provider API and model changes.
Manage releases through testing, type checks, backups, migrations, deployment, smoke testing, change records, and rollback procedures.
Support workspaces, model routing, user administration, and upgrades on self-hosted AI platforms.
Complete weekly application health checks, monthly dependency updates, and quarterly security scans. Maintain staging environments and rehearse rollback procedures.
Maintain application-specific model-provider credentials with spending caps, named owners, rotation dates, and alerts. Review spend weekly, investigate unusual increases, and respond to exposed credentials.
Review AI interactions monthly for answer quality, hallucinations, prompt injection, abuse, errors, and token usage. Improve prompts, guardrails, and routing, and report cost per feature.
Maintain evaluation datasets, test prompt and model changes before release, and check for production quality drift. Track model retirements and validate replacements in staging.
Document provider data-retention, training opt-out, and residency settings. Maintain moderation, personal-data protection, retention controls, and least-privilege tool access.
Apply secure delivery checks covering secrets, dependencies, input validation, authentication, sessions, and file uploads. Require human review of AI-assisted changes before production.
Verify weekly database and object-storage backups, maintain structured logs, and troubleshoot database and application performance.
Provide first-line user support and maintain FAQs and runbooks. Participate in the alternate-week application on-call rota, respond to Severity 1 incidents within 15 minutes while on call, and document incident reviews.
Required Skills and Experience
3–6 years building and supporting web applications, including at least one year integrating LLM APIs in production.
Strong Node.js/TypeScript and Python skills, including Express or similar frameworks, React or Next.js, and FastAPI or Flask.
Production model-provider API experience covering streaming, function calling, rate limits, token accounting, cost controls, prompt-injection defences, and evaluations.
Experience with platform-as-a-service deployments and production secrets management. Replit is preferred; Vercel, Render, or Railway experience is acceptable with willingness to learn Replit.
PostgreSQL migrations, backups, and query troubleshooting; experience with Redis and background workers such as Celery or BullMQ.
Knowledge of application security, dependency auditing, secret scanning, authentication, and session handling.
Experience with Git/GitHub, pull requests, branch protection, CI checks, and Docker for reproducing issues.
Clear communication with non-technical users, patient support, and ownership of production issues.
Preferred Skills
pgvector, retrieval pipelines, and administration of platforms such as Dify or LibreChat.
Voice and avatar integrations such as LiveKit or HeyGen, and video rendering with Remotion.
AWS services such as S3 and Lambda.
Awareness of data privacy requirements for learner and candidate information.
Selection process: Shortlisted candidates complete a two-hour practical exercise on a sample environment before interview.
Most IT Jobs posts in Mumbai ask for 3–6 years of experience (47% of 738 that say).
Hiring most for IT Jobs in Mumbai
JPMorgan Chase67 open jobs
BNP Paribas India Solutions60 open jobs
Necsws27 open jobs
Jobs asking for Application Security in Mumbai also ask for
SQL55%
Secure Coding45%
JavaScript45%
REST API Development45%
Python45%
From live job posts on CoreHRx, updated 21 Nov 2026. Skill figures count posts that list their skills; salary figures only posts that show a salary.
Questions about this job
What is the salary for this Application & AI Operations Engineer job?
The post does not state the pay. As an estimate, comparable posts on CoreHRx advertise ₹11L – ₹28L a year (typical for IT Jobs in Maharashtra, 119 posts).
This guide is for freshers in India preparing for DevOps, cloud or backend roles, and for experienced developers and SREs facing a Docker and Kubernetes round at a Pune IT services firm or a Bengaluru product company. It has 60 questions in three levels: easy questions on images, containers, Dockerfiles, Compose and the core Kubernetes objects; medium questions on multi-stage builds, probes, resources, autoscaling, rollouts, Helm and debugging failing pods; and hard questions on internals, scheduling, security, zero-downtime releases and cluster design. Versions are named wherever behaviour changed. Try each file and command on your laptop or a local cluster, then explain the answer aloud.
Questions you may be asked
What is a container, and how is it different from a virtual machine?
What is the difference between a Docker image and a container?
Walk through this Dockerfile. What does each instruction do?
What is the difference between CMD and ENTRYPOINT in a Dockerfile?