AI Enablement Engineer

Crescendo Global Leadership Hiring India; Chennai; On-site; INR 1,500,000 - 2,500,000; Full time

Job summary

Crescendo Global Leadership Hiring India is seeking a seasoned software engineer to lead AI-driven software engineering initiatives in Chennai. You will identify bottlenecks, prioritize high-value AI use cases, and partner with teams to design and deploy RAG-powered tooling.

The role requires hands-on experience with production systems, AI integrations, and mentoring engineers, while ensuring secure data handling and robust testing across pipelines and deployments.

Qualifications

• Hands-on production software engineering experience with APIs and CI/CD.
• Experience applying AI to software engineering workflows and LLM integrations.
• Ability to design RAG capabilities with safeguard and human oversight.

Responsibilities

• Identify bottlenecks and prioritize AI use cases from requirements to rollout.
• Evaluate and integrate AI tools with repos and delivery workflows.
• Design and implement RAG capabilities including embeddings and vector search.
• Collaborate with engineers through demonstrations and workshops.
• Establish support responsibilities and handover with owners.
• Ensure human-reviewed AI outputs, tests, and secure data handling.

Skills

Software engineering

APIs

CI/CD

LLM integrations

RAG pipelines

Mentoring engineers

Security/compliance

Tools

Core Java

Python scripting

Cloud platforms

Kubernetes

Version control

CI/CD tools

Job description

Core responsibilities-

• Identify engineering bottlenecks and prioritize internal AI use cases based on expected value, feasibility and risk. Address selected workflows across requirements, design, coding, review, testing, documentation, release and support.
• Evaluate and integrate approved AI tools with repositories, development environments, knowledge sources and delivery workflows. Build supporting scripts, APIs or services where needed.
• Design and implement retrieval-augmented generation (RAG) capabilities for internal engineering needs, covering ingestion, chunking, embeddings, vector search, retrieval quality, access controls and guardrails.
• Pair with engineers on real tasks, run practical demonstrations and workshops, and adapt guidance to each team's experience, technical stack and feedback.
• Guide selected use cases from discovery through pilots and rollout. Work with engineering, platform and security owners to establish support responsibilities and handover.
• Apply engineering judgment to AI-generated code and recommendations. Maintain human review, automated tests, CI checks, secure data handling and production reliability.
• Create reusable prompts, repository guidance, examples and playbooks. Develop team champions and transfer knowledge so practices continue after the engagement.
• Establish baselines and measure adoption alongside engineering outcomes, such as task turnaround, review effort, rework, test reliability and developer experience.

Required capabilities-

• Strong hands-on software engineering experience in production environments, with the ability to understand existing codebases and contribute to implementation, debugging, testing and code review. Working knowledge of APIs, source control and CI/CD is essential.
• Practical experience applying AI to software engineering workflows, with clear examples of personal contribution and how other engineers used the resulting tools or practices.
• Experience implementing large language model (LLM) integrations and RAG, including retrieval evaluation, grounding, failure handling and appropriate human oversight.
• Experience mentoring or enabling engineers, explaining technical decisions, responding to feedback and helping teams adopt new working practices.
• Ability to work within approved tooling, repository permissions and data-handling policies, protecting proprietary code, confidential information, secrets and personal data.

Preferred experience-

• Core Java, microservices, cloud platforms or legacy modernization.
• Python for scripting, automation and AI integrations.
• Agentic workflows, tool calling, context and memory management, and human-in-the-loop controls.
• LLMOps practices, including evaluation, prompt and version management, observability, cost optimization and governance.