Role : LLM Integration & CI/CD Engineer

Level : Senior Associate

Tower : AI Operations & Platform Support (AI Managed Services)

Experience : 6+ years in DevOps, release engineering, API integration engineering, or a similar L2/L3 support role

Work Location : Bangalore / Hyderabad

Key Platforms : AWS, GitHub Actions / Jenkins / Azure DevOps, OpenAI / Bedrock integrations, ITSM and observability tooling

Role profile

Senior hands-on engineer who can troubleshoot integrations, operate CI/CD pipelines, and support controlled releases in an enterprise-managed-services model.

Primary focus

APIs and connectors, deployment pipelines, secrets and IAM, release governance, rollback readiness, and L2/L3 troubleshooting.

Best fit

Someone who can balance speed with control, understands why releases fail, and can drive issues to closure across engineering, platform, and security stakeholders.

Role Summary

As an LLM Integration & CI/CD Engineer, you will support the non-production to production path for in-scope AI services and integrations. You will help build and operate repeatable deployment patterns, investigate pipeline and connector failures, coordinate release readiness, and improve the reliability and maintainability of the integration landscape. We are looking for engineers who do not just deploy code, but can reason through operational risk, rollback paths, configuration dependencies, and stakeholder impacts.

Key Responsibilities

1. Integration and connector engineering

- Build, support, and troubleshoot API-based integrations across in-scope AI platforms and enterprise systems.
- Implement resilient integration patterns such as retries, idempotency, error handling, timeouts, and operational telemetry.
- Work through authentication, configuration, payload, and dependency issues across application and platform boundaries.

2. CI/CD and release operations

- Build and maintain CI/CD pipelines for AI workloads and supporting services, with explicit validation, promotion, and rollback steps.
- Operate pipelines in line with change and release governance and support safe promotion through environments.




- Standardize templates, checks, and reusable workflows to reduce release risk and improve consistency.

3. Secure delivery and operational readiness

- Implement secure secrets handling, service-account management, and least-privilege access patterns for integrations and pipelines.
- Coordinate release readiness activities including deployment plans, rollback paths, runbook updates, and post-release verification.
- Support high-risk or time-sensitive changes in partnership with the incident commander and broader platform team.

4. Troubleshooting and continuous improvement

- Provide L2/L3 support for pipeline failures, integration defects, and deployment-related incidents.
- Drive corrective actions that improve supportability, reliability, and developer experience without weakening controls.
- Maintain pipeline and integration documentation, escalation paths, and common-failure reference material.

Preferred Skills and Experience

Skill area

Preferred background

API and integration engineering

Hands-on experience designing, supporting, and troubleshooting APIs, connectors, webhooks, and enterprise integrations.

CI/CD and DevOps

Experience building and operating CI/CD pipelines using tools such as GitHub Actions, Jenkins, Azure DevOps, or similar.

Cloud deployment patterns

Working knowledge of AWS services and deployment patterns for enterprise applications or AI workloads, including configuration promotion and operational validation.

IAM and secrets management

Experience implementing secure delivery practices using least privilege, secrets management, service accounts, RBAC, and approvals.

Release and change governance

Experience operating within ITIL-aligned incident, request,



release, and change-management processes.

Critical thinking and stakeholder engagement

Ability to reason through ambiguous failures, synthesize technical and operational risk, and work effectively with platform owners, security teams, and business stakeholders.

Nice to Have

- Experience with Terraform or adjacent infrastructure-as-code tooling.
- Familiarity with Bedrock, OpenAI, or other enterprise GenAI service integrations.
- Experience supporting post-deployment validation, rollback exercises, and emergency changes.
- Strong working knowledge of ServiceNow or similar ITSM tooling.

Working Style & Core Behaviors

- Approaches failures methodically and can separate symptom from cause.
- Understands that stable delivery is as important as fast delivery.
- Is comfortable driving follow-ups across multiple resolver groups and does not wait passively for answers.
- Documents patterns and fixes so the team becomes less dependent on tribal knowledge.

What Good Looks Like

- Can diagnose whether a failed release is caused by code, config, IAM, pipeline logic, or environment drift.
- Creates deployment patterns that are easy to support, easy to validate, and easy to roll back.
- Improves integration resilience rather than repeatedly fixing the same class of issue.
- Keeps change execution controlled while still helping the team move quickly.

Team Context

You will join PwCs AI Operations & Platform Support team supporting clients run-state AI environment. The operating model is centered on Level 2 and Level 3 support, monitoring, incident response, service requests, minor enhancements, and continuous improvement across AWS/Bedrock, OpenAI, and related platform components.

This role will work in a managed-services model focused on incident management, service requests, monitoring, minor enhancements, knowledge management, and continuous improvement. Success depends not only on technical skill, but also on ownership, collaboration, and the ability to engage stakeholders to progress work.

📌 LLM Integration and CICD Engineer (Hyderabad)
🏢 PwC
📍 Hyderabad