Java Fullstack + AI _D-2662

KEY RESPONSIBILITIES

• Design, develop, and enhance backend services and APIs using Java and Spring Boot.
• Build high-throughput and resilient event-driven components using Kafka.
• Work with MongoDB or other NoSQL databases to design efficient data models and optimize queries.
• Integrate Large Language Models (LLMs) such as OpenAI, Claude, or Gemini into backend services via REST APIs and SDKs.
• Build and maintain AI-powered microservices including RAG (Retrieval-Augmented Generation) pipelines, semantic search, and document intelligence features.
• Develop and expose AI agent workflows using frameworks such as LangChain4j, Spring AI, or similar Java-native AI toolkits.
• Implement prompt engineering strategies, context management, and output validation layers for LLM interactions.
• Design vector database integrations (Pinecone, Weaviate, pgvector) for embedding storage and similarity search.
• Collaborate closely with architects, BAs, and cross-functional teams to deliver robust technical solutions.
• Participate in code reviews, refactoring efforts, and optimisation of system performance.
• Ensure best practices for coding standards, security, maintainability, and AI model governance.
• Troubleshoot production issues and provide root cause analysis and long-term fixes.
• Support CI/CD pipeline integration, model deployment automation, and MLOps tooling.
• Contribute to documentation, technical specifications, and architectural diagrams.

REQUIRED SKILLS & QUALIFICATIONS

• 5+ years of hands-on development experience in Java-based applications.
• Strong expertise in Java (8/11/17), Spring Framework, Spring Boot, and RESTful services.
• Experience with Kafka for messaging, streaming, or event-driven architecture.
• Practical knowledge of MongoDB or other NoSQL databases (e.g., Cassandra, DynamoDB, Couchbase).
• Solid understanding of microservices architecture and distributed systems.
• Hands-on experience consuming LLM APIs (OpenAI GPT-4o, Anthropic Claude, Google Gemini) in production Java applications.
• Familiarity with Spring AI or LangChain4j for building LLM-backed services in Java ecosystems.
• Experience with prompt engineering — crafting, versioning, and testing prompts for accuracy, safety, and cost efficiency.
• Knowledge of embedding models and vector stores for semantic search and RAG pipelines.
• Strong debugging, analytical, and problem-solving skills.
• Experience with Git, Maven/Gradle, Jenkins, Docker, or Kubernetes is a plus.
• Excellent communication and collaboration skills.

PREFERRED SKILLS

• Experience working in the Insurance domain (Policy, Claims, Underwriting, Billing, etc.).
• Hands-on experience building or fine-tuning ML models using Python-based frameworks (Hugging Face, scikit-learn, PyTorch) integrated with Java services.
• Exposure to AI agent orchestration tools — LangGraph, AutoGen, CrewAI, or OpenAI Assistants API.
• Experience deploying models on cloud AI services: AWS Bedrock, Azure OpenAI Service, or Google Vertex AI.
• Familiarity with MLOps platforms (MLflow, SageMaker, Kubeflow) for experiment tracking and model lifecycle management.
• Knowledge of AI safety, responsible AI practices, and PII/data privacy considerations when working with LLMs.
• Exposure to cloud platforms such as AWS, Azure, or GCP.
• Knowledge of caching frameworks (Redis, Hazelcast) for LLM response caching and rate-limit management.
• Familiarity with containerization and orchestration platforms.
  • Understanding of DevOps principles and observability tools (Grafana, Prometheus, ELK) — including LLM observability (token usage, latency, hallucination monitoring).