Inviting applications for the role of Manager, Full Stack Application Development (Agentic AI)

We are seeking a highly skilled hands-on engineer who combines strong Full Stack Development capabilities with modern Agentic AI expertise, capable of building customer-facing digital platforms, AI copilots, RAG applications, and autonomous agent workflows while maintaining enterprise-grade standards for scalability, security, resiliency, observability, and user experience. This role requires strong full-stack engineering capabilities across frontend, backend, APIs, cloud-native architectures, and DevOps, combined with hands-on experience in Generative AI, AI Agents, Retrieval-Augmented Generation (RAG), and LLM orchestration.

Responsibilities:

Full Stack Application Development

- Design, develop, and support client-facing web applications, digital platforms, APIs, and enterprise solutions.
- Build modern, responsive, and intuitive user interfaces using React, Angular, TypeScript, JavaScript, HTML5, and CSS.
- Develop scalable backend services using Python (FastAPI), Java Spring Boot, Node.js, or equivalent technologies.
- Design and implement secure REST APIs, microservices, and event-driven architectures.
- Translate business requirements into scalable technical solutions through direct engagement with business stakeholders.
- Own the complete software development lifecycle from concept, design, development, testing, deployment, and production support.
- Deliver highly available, resilient, secure, and performant applications.
- Drive modernization initiatives using cloud-native, API-first, and microservices-based architectures.

Agentic AI Development

- Design and build AI agents capable of reasoning, planning, tool utilization, and executing multi-step tasks autonomously.
- Develop intelligent workflows using LangGraph, LangChain, Semantic Kernel, CrewAI, AutoGen, or similar frameworks.
- Design and implement multi-agent systems comprising planners, executors, evaluators, orchestrators, and domain-specific agents.
- Build agent memory systems, checkpointing, state management, guardrails, escalation mechanisms, and human-in-the-loop workflows.
- Develop AI-enabled capabilities that improve operational efficiency, client experience, and business workflows.
- Implement workflow orchestration, tool-calling, and autonomous decision-making capabilities using Large Language Models.
- Evaluate and optimize agent performance, reasoning quality, task completion, and reliability.
- Develop calibration frameworks and guardrails to improve agent accuracy and reduce hallucinations.

MCP & AI Platform Engineering

- Design, develop, and maintain Model Context Protocol (MCP)



servers and enterprise AI integration frameworks.
- Build reusable MCP tools, resources, prompts, and connectors.
- Develop scalable processes for onboarding and registering enterprise tools within MCP ecosystems.
- Enable AI agents to securely interact with enterprise systems, APIs, business applications, and databases.
- Develop reusable AI platform components supporting orchestration, memory, governance, and tool execution.

RAG & Knowledge Systems

- Design and implement enterprise-grade Retrieval-Augmented Generation (RAG) solutions.
- Develop document ingestion, chunking, indexing, retrieval, and ranking pipelines.
- Implement semantic search, hybrid retrieval, metadata filtering, and contextual reasoning capabilities.
- Work with embeddings and vector databases including Azure AI Search, Pinecone, FAISS, ChromaDB, and Weaviate.
- Optimize AI applications for groundedness, accuracy, relevance, latency, scalability, and cost efficiency.
- Evaluate retrieval and generation quality using standardized AI evaluation frameworks.

Cloud, DevOps & Platform Engineering

- Deploy and manage cloud-native applications on Azure.
- Build and maintain CI/CD pipelines, automated testing frameworks, and deployment automation processes.
- Develop and manage containerized workloads using Docker and Kubernetes.
- Implement Infrastructure-as-Code and DevSecOps best practices.
- Ensure operational excellence, security, reliability, and scalability across distributed systems.
- Collaborate with platform and cloud engineering teams to deliver enterprise-scale AI and digital solutions.

Observability & Monitoring

- Configure OpenTelemetry instrumentation, distributed tracing, metrics, and logging.
- Monitor application performance, AI agent executions, model calls, API requests, workflow latency, and infrastructure utilization.
- Integrate telemetry with Grafana, Azure Monitor, Application Insights, Galileo, or equivalent observability platforms.
- Build dashboards and alerts to proactively identify failures, bottlenecks, anomalies, and production issues.
- Lead troubleshooting and production debugging of distributed applications and AI systems.

Enterprise Data Integration

- Design and build integrations with MongoDB, PostgreSQL, SQL Server, Snowflake,



and enterprise data platforms.
- Develop APIs and services supporting transactional and analytical workloads.
- Integrate AI applications with enterprise systems, workflow engines, document repositories, and business platforms.
- Ensure secure handling of credentials, secrets, API keys, service identities, and authentication tokens.

Qualifications we seek in you!

Minimum Qualifications

- Bachelor's or Master's degree in Computer Science, Engineering, Information Technology, or a related field.
- Relevant years of professional software engineering experience.
- Strong experience building enterprise-scale full stack applications.
- Proven experience delivering secure, scalable, customer-facing applications.
- Experience working independently while driving large and complex initiatives.
- Strong stakeholder management, communication, and problem-solving capabilities.

Technical Skills

Full Stack Development

- Solid programming expertise in Python.
- Experience with FastAPI, Spring Boot, Node.js, or similar backend frameworks.
- Proficiency in React, Angular, TypeScript, JavaScript, HTML5, and CSS3.
- Experience building REST APIs, microservices, and enterprise web applications.
- Strong understanding of software design patterns, scalable architectures, and secure coding practices.

Agentic AI & GenAI
- Hands-on experience with LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI, or similar agent frameworks.
- Experience building AI agents, multi-agent systems, AI copilots, and workflow automation solutions.
- Strong understanding of RAG, prompt engineering, tool calling, agent memory, orchestration, and AI evaluation frameworks.
- Experience with embeddings, vector databases, and semantic search technologies.

Cloud & DevOps
- Experience with Azure OpenAI, Azure AI Search, Azure Functions, App Services, and AKS.
- Knowledge of Docker, Kubernetes, CI/CD pipelines, and cloud-native application development.
- Familiarity with monitoring, observability, and OpenTelemetry.

Data & Integration
- Experience with MongoDB, SQL Server, PostgreSQL, Snowflake, or similar databases.
- Strong understanding of API integration, enterprise application integration, authentication, and authorization frameworks (OAuth/OIDC).

Architecture & Engineering
- Strong understanding of microservices, distributed systems, scalability, resiliency, and performance optimization.
- Experience designing modular, reusable, and enterprise-grade applications.
- Excellent problem-solving, stakeholder management, and communication skills

Interested candidate share their profile at [email protected]

📌 Urgent Hiring_Full Stack with Agentic AI (Bengaluru)
🏢 Genpact
📍 Bengaluru