About the role
Synechron is seeking a Java Developer with Generative AI expertise to design, develop, and integrate AI-powered applications.
The role will combine strong Java-based backend development with hands-on experience in Large Language Models, AI frameworks, cloud technologies, prompt engineering, Retrieval-Augmented Generation, embeddings, and vector databases.
The position will contribute to business objectives by delivering scalable AI-enabled applications, intelligent automation, chatbots, copilots, search solutions, and secure enterprise technology services.
Software Requirements:
- Required Software Skills
- Java: Strong professional experience in Java application development.
- Spring Boot: Hands-on experience developing scalable backend applications and services.
- Microservices: Experience designing, developing, integrating, and supporting microservices.
- REST APIs: Proficiency in designing, developing, integrating, and securing RESTful APIs.
- Distributed systems: Understanding of distributed-system principles, service communication, scalability, reliability, and fault handling.
- Generative AI and LLMs: Hands-on experience developing or integrating solutions using Large Language Models.
- AI platforms: Experience with OpenAI, Azure OpenAI, Gemini, Anthropic Claude, or equivalent AI platforms.
- AI orchestration frameworks: Experience with LangChain, LlamaIndex, Semantic Kernel, or similar frameworks.
- Prompt engineering: Knowledge of prompt design, testing, optimization, grounding, and response evaluation.
- RAG: Experience designing or implementing Retrieval-Augmented Generation architectures.
- Embeddings and vector databases: Knowledge of embeddings, semantic search, indexing, retrieval, and vector databases such as Pinecone, ChromaDB, FAISS, Weaviate, or equivalent technologies.
- Databases: Good understanding of SQL and NoSQL databases.
- Development and deployment tools: Experience with Git, CI/CD, Docker, and Kubernetes.
- Cloud platforms: Experience with Azure, AWS, or GCP.
- Agile practices: Experience working in Agile development environments and participating in code reviews.
Preferred Software Skills:
- Python for AI/ML integrations.
- Knowledge of AI governance, model evaluation, and responsible AI practices.
- Exposure to MLOps and AI deployment frameworks.
- Experience building enterprise-grade Generative AI solutions.
- Familiarity with AI observability, monitoring, logging, and performance evaluation tools.
- Experience with automated testing, deployment validation, and production support for AI applications.
Version and Experience Guidance:
- Specific software versions are not mandated in the requirements.
- Candidates should have experience with current, production-supported versions of Java, Spring Boot, AI frameworks, cloud platforms, databases, Docker, Kubernetes, and CI/CD tools.
- Candidates should be able to assess compatibility, manage upgrades, document changes, and support production lifecycle activities.
- The role requires 5-7 years of overall professional experience, including practical Generative AI and LLM integration experience.
Overall Responsibilities:
- Design, develop, test, deploy, and maintain scalable Java-based applications.
- Build and integrate Generative AI solutions using LLMs.
- Develop AI-powered chatbots, copilots, intelligent search, and automation solutions.
- Implement RAG architectures using embeddings, semantic search, retrieval pipelines, and vector databases.
- Integrate AI models through APIs and AI orchestration frameworks such as LangChain, LlamaIndex, Semantic Kernel, or equivalent tools.
- Develop scalable backend services and microservices using Java and Spring Boot.
- Design and implement RESTful APIs and distributed application services.
- Collaborate with business stakeholders and cross-functional teams to gather requirements and deliver practical solutions.
- Optimize the performance, security, scalability, reliability, latency, and maintainability of AI-enabled applications.
- Work with SQL and NoSQL databases to support application and AI solution requirements.
- Use Git, CI/CD, Docker, Kubernetes, and cloud platforms to support application delivery and deployment.
- Participate in Agile development practices, code reviews, testing, sprint planning, reviews, and retrospectives.
- Document application architecture, API specifications, prompts, data flows, RAG designs, test results, and operational procedures.
- Apply AI governance, data protection, responsible AI, and secure development practices.
- Identify opportunities to improve automation, resource efficiency, application reliability, and sustainable technology operations.
- Contribute to measurable outcomes such as timely feature delivery, improved response quality, reduced defects, reliable releases, and successful adoption of AI-enabled solutions.
Technical Skills (By Category):
Programming Languages:
- Essential
- Strong Java development experience.
- Strong understanding of object-oriented programming, design principles, exception handling, testing, and maintainable code.
- Experience developing Java-based APIs, microservices, integrations, and backend services.
- Ability to write modular, scalable, testable, secure, and production-ready code.
- Preferred
- Python for AI/ML integrations, data preparation, automation, and model interaction.
- Experience with additional programming or scripting languages used in cloud-native and AI application development.
- Familiarity with asynchronous, event-driven, and distributed application development.
Databases/Data Management:
- Essential
- Good understanding of SQL databases.
- Good understanding of NoSQL databases.
- Ability to design data access patterns, queries, schemas, and application integrations.
- Understanding of embeddings, metadata, semantic search, vector indexing, retrieval, and ranking.
- Experience working with vector databases such as Pinecone, ChromaDB, FAISS, Weaviate, or equivalent technologies.
- Understanding of data quality, access control, data protection, retention, and responsible data usage.
- Preferred
- Experience with data pipelines supporting RAG applications.
- Familiarity with document processing, chunking, metadata tagging, and data ingestion.
- Exposure to data validation, reconciliation, lineage, and knowledge-base management.
- Experience with data preparation for model evaluation or domain-specific AI solutions.
Cloud Technologies:
- Essential
- Experience with Azure, AWS, or GCP.
- Understanding of cloud-native application development and deployment.
- Experience with cloud compute, storage, networking, identity, monitoring, security, and service integration.
- Ability to deploy and support AI-enabled applications across development, testing, staging, and production environments.
- Understanding of scalability, availability, reliability, and cloud resource management.
- Preferred
- Experience with cloud-based AI and machine-learning services.
- Familiarity with serverless services, managed databases, container orchestration, and infrastructure automation.
- Exposure to MLOps, model deployment, AI observability, and cloud-based evaluation platforms.
- Understanding of cloud cost optimization and sustainable AI workload design.
Frameworks and Libraries:
- Essential
- Java and Spring Boot.
- Microservices frameworks and REST API technologies.
- LangChain, LlamaIndex, Semantic Kernel, or equivalent AI orchestration frameworks.
- RAG architectures and related retrieval frameworks.
- Embedding generation, vector search, semantic retrieval, and indexing technologies.
- Integration with OpenAI, Azure OpenAI, Gemini, Anthropic Claude, or equivalent AI platforms.
- SQL and NoSQL data-access frameworks.
- Docker and Kubernetes.
- Preferred
- Python-based AI/ML frameworks and libraries.
- AI model evaluation, observability, monitoring, and deployment frameworks.
- MLOps and LLMOps tools.
- Frameworks supporting prompt management, model routing, response validation, and AI safety.
- Libraries supporting automated testing, performance evaluation, and distributed tracing.
Development Tools and Methodologies:
- Essential
- Experience across the software development lifecycle, including requirements analysis, design, development, testing, deployment, support, and maintenance.
- Experience with Git and collaborative version-control practices.
- Experience with CI/CD pipelines, automated builds, testing, deployments, and release management.
- Experience with Docker and Kubernetes-based application deployment.
- Experience participating in code reviews and applying coding and quality standards.
- Knowledge of Agile development practices.
- Ability to create technical designs, API documentation, prompt documentation, test cases, deployment procedures, and operational runbooks.
- Experience testing AI-enabled applications, APIs, RAG workflows, integrations, and application behavior.
- Preferred
- Exposure to MLOps and AI deployment frameworks.
- Experience with automated AI evaluation, regression testing, monitoring, and alerting.
- Familiarity with infrastructure as code and deployment automation.
- Experience with production support, incident management, and performance optimization.
- Exposure to iterative product development and continuous improvement practices.
Security Protocols:
- Essential
- Understanding of secure Java, API, microservices, database, and cloud application development.
- Knowledge of authentication, authorization, access controls, secrets management, and secure configuration.
- Understanding of AI risks, including prompt injection, data leakage, unauthorized model access, unsafe responses, and insecure tool or API use.
- Ability to apply input validation, output validation, data protection, and secure integration practices.
- Understanding of responsible AI, privacy, governance, traceability, and human oversight.
- Ability to protect sensitive data used in prompts, embeddings, vector databases, model interactions, and application workflows.
- Preferred
- Experience with AI governance, model evaluation, responsible AI, and AI risk controls.
- Familiarity with OAuth 2.0, OpenID Connect, encryption, and secure service-to-service communication.
- Experience with threat modeling, security testing, vulnerability remediation, and compliance controls.
- Exposure to security validation within CI/CD, MLOps, LLMOps, and cloud deployment workflows.
Experience Requirements:
- Overall experience: 5-7 years of professional software development experience.
- Java experience: Strong hands-on experience with Java, Spring Boot, microservices, REST APIs, and distributed systems.
- Generative AI experience: Hands-on experience with Generative AI and Large Language Models.
- RAG experience: Experience with RAG, prompt engineering, embeddings, vector databases, semantic search, and retrieval workflows.
- AI framework experience: Experience with LangChain, LlamaIndex, Semantic Kernel, or equivalent AI orchestration frameworks.
- Cloud experience: Experience with Azure, AWS, or GCP.
- Database experience: Good understanding of SQL and NoSQL databases.
- Engineering experience: Experience with Git, CI/CD, Docker, Kubernetes, Agile delivery, code reviews, testing, and production support.
- Preferred experience: Experience building enterprise-grade GenAI solutions, applying AI governance, supporting model evaluation, and implementing MLOps practices.
- Industry preference: Experience delivering secure, scalable, regulated, or business-critical enterprise applications is preferred.
- Alternative experience pathways: Equivalent combinations of relevant Java development, AI integration, technical training, substantial project delivery, open-source contributions, or demonstrable production implementations may be considered.
- Outcome evidence: Candidates should demonstrate contributions to reliable AI applications, improved retrieval quality, reduced manual effort, successful application delivery, improved performance, or production adoption of Generative AI solutions.
Day-to-Day Activities:
- Design, develop, test, and maintain Java Spring Boot microservices, REST APIs, AI integrations, RAG pipelines, vector database solutions, and application services.
- Collaborate with business stakeholders, product teams, data specialists, engineering teams, and security stakeholders through Agile ceremonies, design discussions, code reviews, and planning sessions.
- Deliver production-quality code, prompts, API integrations, technical documentation, test results, deployment artifacts, evaluation outputs, and operational updates.
- Make technical decisions within the assigned scope and raise risks or recommendations related to AI quality, security, privacy, performance, scalability, cost, and reliability.
Qualifications:
Bachelor's or Master's degree in Computer Science, Information Technology, Engineering, or a re