AI Platform Developer Specialist

Overview

Build, maintain and evolve FNZ's Client Application Deployment Framework and internal Launchpad, so AI services (AI Foundry, LLMs, RAG platforms, MCP gateways, model serving, storage, caching) are delivered with the same engineering standards, governance, operational processes and FinOps principles as the wider platform.

What you'll do

• Design, develop and maintain reusable cloud infrastructure and platform capabilities using Terraform, Azure, Kubernetes and Infrastructure-as-Code best practices.
• Implement and operate AI infrastructure services including Azure AI Foundry, LLM platforms, MCP gateways, RAG solutions, vector databases, storage and caching services.
• Build, maintain and optimise CI/CD pipelines, automation frameworks and deployment processes using GitHub and GitHub Actions.
• Enable product teams to securely deploy and consume AI and cloud services through standardised platform patterns, self-service capabilities and golden paths.
• Implement security, identity, access control, data governance and compliance controls for cloud and AI workloads, including management of sensitive and regulated data.
• Establish observability, monitoring, distributed tracing, logging and usage instrumentation to ensure platform reliability and AI workload performance.
• Drive FinOps and cost optimisation initiatives by implementing infrastructure, cloud and AI service usage monitoring, reporting and governance controls.
• Support lifecycle management of AI services and models, including onboarding, upgrades, deprecation planning, rollout of new capabilities and operational support.
• Collaborate with Product, Platform Engineering, Security, AI Governance and Operations teams to design scalable, secure and resilient platform solutions.
• Evaluate emerging cloud, AI and Platform Engineering technologies and contribute to continuous improvement of FNZ's Application Deployment Framework and platform strategy.
• Implement infrastructure architecture to support agentic workloads, including models, LLM and MCP gateways, RAG, storage and caching for agentic loops and inference.
• Implement data governance controls such as access control and handling of PII within RAG stores.
• Assist product teams with configuration and deployment of infrastructure aligned to their use cases, including cost and usage instrumentation (e.g. token/API usage) and access controls around LLM and tool usage.
• Provide an escalation point for AI-related production support queries.
• Participate in monitoring and feedback loops between AI Governance, Product and Project teams, including model version deprecation, preview evaluations and rollout of replacement models.
• Assist InfoSec and project teams with stale or toxic data and memory cleanup as needed.

What you'll need

• Bachelor's degree or higher (min A- average for under-graduate, first class for post-graduate).
• Experience deploying and operating LLM-based solutions in Azure or other major cloud providers.
• Experience with MCP (Model Context Protocol).
• Familiarity with AI gateways, model routing and model management platforms.
• Experience implementing RAG solutions including vector databases, caching strategies and retrieval pipelines.
• Understanding of agent orchestration frameworks.
• Knowledge of AI security and governance controls.
• Experience implementing data residency and regulatory compliance requirements.
• Experience building reusable platforms, developer self-service capabilities and golden-path architectures.
• Experience developing Terraform modules, providers or reusable infrastructure frameworks.
• Experience with HashiCorp Vault, Key Vault or equivalent secret-management technologies.
• Essential skills: Terraform and Infrastructure-as-Code; Kubernetes (production operations and troubleshooting); GitHub / GitHub Actions; Open Telemetry and distributed tracing; monitoring and logging platforms; LLM, RAG and MCP.

Nice to have

• Microsoft Azure experience.
• Microsoft Azure (preferred).
• Azure AI Foundry (preferred).
• Azure networking and hybrid connectivity (preferred).

Details

• Location: Gurugram, India.
• Flexible and agile working arrangement.