New opportunity

Lead Engineer Architect (Java / Spring Boot / AI Engineering)

Vivantify Technology Solutions India Private Limited · Pune, India

About this role

We are seeking a Lead Engineer / Architect with strong expertise in Java 17, Spring Boot, Python, and AI/LLM engineering to design and build scalable enterprise applications. The role emphasizes AI agents, Model Context Protocol (MCP), vector databases, and graph databases, alongside distributed systems and solution architecture.

Responsibilities

Design and implement enterprise-scale architectures using Java 17, Spring Boot, and Python.
Develop loosely coupled, domain-driven, microservices-based, and event-driven solutions.
Architect AI-enabled services involving LLMs, AI agents, MCP integrations, and orchestration frameworks.
Integrate vector databases, semantic search, graph databases, and knowledge graph technologies into AI solutions.
Design efficient SQL and NoSQL data models and optimize data access using caching technologies.
Lead hands-on development, code reviews, architecture decisions, and engineering best practices.
Implement secure APIs, system integrations, monitoring, and performance optimization.
Collaborate with cross-functional teams to manage delivery priorities, technical risks, and architectural trade-offs.

Required qualifications

Java 17
Spring Boot
Python development
Solution architecture and enterprise application design
AI/LLM development, AI agents, and related frameworks
Model Context Protocol (MCP) and AI orchestration patterns
SQL and NoSQL databases
Vector databases and semantic search
Graph databases, GraphDB, and graph-based data modeling
Microservices, API-first design, and distributed systems
ORM frameworks and messaging technologies such as Kafka or MQ
Caching technologies such as Redis and Apache Ignite
Observability and performance monitoring using Splunk, Dynatrace, or equivalent tools
API security and secure AI component integration

Preferred qualifications

Experience with Solr, Lucene, or equivalent search technologies
Hands-on implementation of GraphDB and knowledge graph solutions
Exposure to LLM integration, vector databases, and prompt orchestration frameworks
Experience with large-scale system observability, monitoring, and performance optimization

Benefits

Competitive salary and benefits package
Opportunities for professional growth and development
A collaborative and inclusive work environment
The opportunity to work on exciting and challenging projects with leading clients

For full details about this role, click “Apply on company site” to view the employer’s original posting.

Skills for this role

Java 17Spring BootPythonSolution architectureAI/LLM developmentAI agentsModel Context Protocol (MCP)SQLNoSQLVector databasesGraph databasesMicroservicesKafkaRedisApache IgniteSplunkDynatraceSolrLucene

Checking your profile…

Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.

Understand the role

What matters most

Enterprise AI Architecture & Agent Integration
Design scalable enterprise applications integrating LLMs, AI agents, and Model Context Protocol (MCP) orchestration patterns alongside core Java 17 and Python services.
Graph & Vector Data Modeling
Implement and optimize graph databases, knowledge graphs, and vector database solutions to support semantic search, inference workflows, and complex context management.
Hands-on Technical Leadership & Governance
Drive architecture decisions, code reviews, and engineering best practices while actively participating in hands-on development across distributed microservices.
Cross-Functional Risk & Performance Management
Collaborate with DevOps, SRE, Data, and Security teams to ensure high observability, secure API design, caching efficiency, and low-latency system performance.

Likely challenges to think through

Balancing AI Non-Determinism with Enterprise Reliability
Integrating stochastic LLM workflows and AI agents into deterministic Java Spring Boot microservices introduces architectural friction. Prepare by establishing strict fallback mechanisms, robust validation layers, and clear boundaries around AI inference outputs.
Complex Multi-Model Data Synchronization
Synchronizing relational, NoSQL, vector, and graph databases simultaneously can create consistency and latency bottlenecks. Prepare by reviewing patterns for dual-write mitigation, caching layers with Redis or Apache Ignite, and efficient context indexing strategies.
Bridging Architectural Governance with Hands-On Coding
As a Lead Engineer Architect, maintaining code contributions while owning enterprise-scale technical decisions requires careful time allocation. Prepare by setting structured code review standards, delegating component-level designs, and utilizing automated CI/CD pipelines.

Practice your answers

Technical practice

Designing Distributed Microservices with Java 17 and Spring Boot

What to coverDiscuss how you structure loosely coupled, domain-driven microservices using Spring Boot. Address strategies for maintaining transaction consistency across distributed boundaries and managing API-first design principles.

Integrating AI Agents and LLM Workflows in Enterprise Apps

What to coverExplain how you incorporate LLMs and autonomous AI agents into enterprise backend services. Candidates should cover orchestration frameworks, managing non-deterministic outputs, and securing AI component integrations.

Utilizing Model Context Protocol (MCP) in Architecture

What to coverDescribe the purpose of the Model Context Protocol (MCP) and how it standardizes context sharing between LLMs and external data sources or tools. Discuss patterns for implementing MCP in secure enterprise environments.

Vector Databases vs. Graph Databases for Semantic Search

What to coverCompare the use cases of vector databases (for semantic search and embedding retrieval) versus graph databases (for knowledge graphs and relationship modeling). Explain when to combine both in an AI-ready platform architecture.

Event-Driven Messaging and Caching Strategies

What to coverExplain how messaging technologies like Kafka or MQ integrate with caching layers such as Redis or Apache Ignite to optimize data access and high-throughput event processing in distributed systems.

Observability and Performance Optimization at Scale

What to coverDetail how you implement large-scale system observability using monitoring tools like Splunk or Dynatrace. Address techniques for tracking latency bottlenecks, tracing distributed requests, and optimizing API performance.

Python Interoperability in Java-Centric Enterprise Systems

What to coverDiscuss architectural patterns for integrating Python-based AI and data science components with a core Java 17 / Spring Boot backend. Address communication overhead, serialization, and deployment trade-offs.

Securing APIs and AI Components in Enterprise Platforms

What to coverExplain best practices for securing REST APIs and integrated AI services against prompt injection, unauthorized data access, and vulnerabilities in distributed systems.

Behavioural practice

Balancing Hands-On Coding with Architectural Leadership

What to coverDescribe a situation where you had to lead high-level architectural decisions while remaining actively involved in hands-on development. Share how you managed your time, resolved technical disagreements, and maintained engineering best practices using the STAR method.

Managing Cross-Functional Risks and Delivery Trade-Offs

What to coverGive an example of collaborating with cross-functional teams (such as DevOps, SRE, Data, and Security) to balance delivery speed against technical risks and architectural trade-offs. Highlight how you communicated risks and reached consensus.

Resolving Complex Technical Disagreements

What to coverDiscuss a time when team members disagreed on a major technology stack or database choice (e.g., relational vs. graph/vector databases). Explain how you evaluated objective criteria, managed stakeholder concerns, and drove a final decision.

Troubleshooting a Critical Production Performance Bottleneck

What to coverShare an experience where you diagnosed and resolved a severe performance or observability issue in a large-scale distributed system using monitoring tools. Outline your investigative steps, root-cause analysis, and preventative measures implemented.

Sharpen your knowledge

Topics to prepare

Enterprise Microservices Architecture & Event-Driven Patterns
Exercise: Design a distributed system architecture document detailing domain-driven boundaries, event-driven message flow using Kafka, and secure API gateways. Relevance: Directly supports the requirement to design loosely coupled, domain-driven, microservices-based, and event-driven enterprise solutions.
AI Agent Orchestration & Model Context Protocol (MCP)
Exercise: Map out an orchestration flow demonstrating how AI agents use the Model Context Protocol (MCP) to interact with external tools and retrieval contexts. Relevance: Directly aligns with the role's primary emphasis on AI agents, MCP integration patterns, and advanced LLM workflows.
Graph and Vector Data Modeling for Semantic Search
Exercise: Design a hybrid schema combining a graph database for knowledge representation and a vector database for semantic search and context retrieval. Relevance: Directly addresses the explicit requirement to integrate vector databases, semantic search, and graph-based data modeling into AI solutions.

Skills to revise

Java 17 & Spring Boot Enterprise Development
Exercise: Build a production-grade backend service using Java 17 and Spring Boot implementing secure REST endpoints, ORM data access, and centralized caching with Redis or Apache Ignite. Relevance: Core technical stack required for hands-on development and architecture leadership.
Python AI & LLM Framework Integration
Exercise: Write a Python module that connects an LLM framework with a vector database to perform semantic querying and automated context management. Relevance: Directly fulfills the requirement for Python development expertise in AI-integrated systems.
System Observability and Performance Monitoring
Exercise: Configure distributed tracing and performance metrics tracking using tools such as Splunk or Dynatrace across microservices. Relevance: Essential for monitoring system performance, API security, and large-scale observability as specified in the role requirements.

Your preparation checklist

Review Java 17 and Spring Boot Microservices Architecture
Completion looks like reviewing design patterns for loosely coupled, domain-driven microservices using Java 17, Spring Boot, event-driven messaging (Kafka or MQ), and caching layers (Redis or Apache Ignite).
Prepare AI Agent and Model Context Protocol (MCP) Walkthrough
Completion looks like outlining a system design or code sample demonstrating AI agent integration, prompt orchestration, and Model Context Protocol (MCP) patterns connecting LLMs with external tools.
Document Vector and Graph Database Integration Strategies
Completion looks like preparing notes and technical diagrams on combining vector databases (for semantic search) and graph databases (for knowledge graphs and graph-based data modeling) in enterprise platforms.
Summarize Python AI Component Interoperability
Completion looks like compiling examples of how Python-based AI/LLM development components interface cleanly with a core Java enterprise backend.
Prepare System Observability and Security Framework Examples
Completion looks like noting practical approaches to API security, secure AI component integration, and distributed tracing using monitoring tools like Splunk or Dynatrace.
Formulate Targeted Technical and Leadership Questions
Completion looks like drafting specific questions for the employer regarding their enterprise microservices architecture, AI agent deployment pipelines, cross-functional collaboration between engineering and SRE/Security teams, and scalability trade-offs.

Availability has not yet been verified. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy

KEEP EXPLORING

Similar AI jobs

Related skills and specializations in India. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…