Agentic AI Engineer Backend & Platform

Please review the JD and apply using the link below. Applying through this below link is mandatory to receive further process updates; otherwise, your application will not be considered.

Link - https://southasiacareers.deloitte.com/job-invite/112404/

The team

Deloittes Technology & Transformation practice can help organizations uncover and unlock value through innovative technology, data, cloud, and AI solutions. Our global network provides strategic guidance and implementation services that help businesses modernize their technology landscape, build scalable digital platforms, and accelerate AI-led transformation. Our practice addresses the continuum of opportunities across cloud, data, artificial intelligence, analytics, software engineering, and next-generation technologies.

Deloitte is building an Agentic Platform & Applications for the enterprise the backend infrastructure that enables businesses to create, deploy, integrate, and operate AI agents at scale in a regulated fintech environment.

Your work profile

We are seeking a strong backend/platform engineer to build and scale the core infrastructure powering enterprise AI agents and applications. The ideal candidate will have solid software engineering fundamentals, experience with distributed systems and cloud-native architectures, and an interest in building production-grade AI agent platforms.

The role will involve:

Building backend services for agent creation, configuration, deployment, execution, sessions, state, memory, and lifecycle the full runtime stack.

Designing and implementing agent and service orchestration capabilities, including asynchronous processing, routing, retries, timeouts, and reliable error handling across multi-agent workflows.

Integrating LLMs, Agent SDKs such as Google ADK and LangGraph, MCP services, and A2A agents through clean, scalable platform APIs.

Connecting AI agents with enterprise applications and services through scalable and versioned APIs.

Building end-to-end production observability using OpenTelemetry, including tracing across agent, model, tool, and service execution.

Deploying and operating platform services on Kubernetes / GKE / GCP with appropriate security, CI/CD, scalability, and production reliability practices.

Working closely with architects, engineers, product teams, and other stakeholders to design and deliver scalable enterprise AI capabilities.

Taking end-to-end ownership of platform components, from design and development through deployment, monitoring, troubleshooting, and continuous improvement.

Key skills required

4-6 years of solid experience in backend or platform engineering.

Strong programming experience in Python, with hands-on experience building production-grade backend services using FastAPI or similar frameworks.

Strong understanding of distributed systems, asynchronous programming, microservices, REST APIs, and scalable backend architectures.

Experience building APIs, developer platforms, orchestration systems, or distributed applications. Experience in AI is beneficial but not mandatory if the candidate has strong transferable platform engineering experience.

Some hands-on exposure to AI agents, Agent SDKs, MCP, A2A, LLM-based applications, or related AI technologies.

Experience with cloud-native architecture and deployment on GCP / GKE, Kubernetes, and Docker.

Understanding of CI/CD, authentication, security, production reliability, and cloud infrastructure practices.

Experience with production observability, distributed tracing, and tools such as OpenTelemetry, OPIK, or Langfuse.

Strong understanding of databases and data stores, including PostgreSQL, Redis, and familiarity with vector databases.

Strong problem-solving, communication, collaboration, and ownership mindset.

Ability to work effectively in a fast-paced environment and take end-to-end ownership of technical deliverables.

Technology Stack

Platform

• Python
• FastAPI
• REST APIs
• Async
• Microservices
• Auth

Agents

• Google ADK
• LangGraph
• MCP
• A2A
• Agent Runtime

LLMs

• OpenAI
• Gemini
• Anthropic
• Model Gateway / Streaming

Infrastructure

• GCP
• GKE
• Kubernetes
• Docker
• CI/CD

Observability

• OpenTelemetry
• Distributed Tracing
• OPIK / Langfuse

Data

• PostgreSQL
• Redis
• Vector DBs

Qualifications

Bachelors or Masters degree in Computer Science, Engineering, or a related field.