Duration: Initial contract till year end, we expect to extend 6months+
Role Description
Must-have skills & experience
3-6 years of hands-on experience building full stack applications using Java and the Spring Boot framework (or equivalent) in a production environment.
Experience working in a large enterprise or complex organization (multiple teams, services, stakeholders).
Solid backend development skills: Java 8+, Spring Boot, RESTful APIs, data access (JPA/Hibernate), relational databases (e.g., PostgreSQL, MySQL) and familiarity with NoSQL as a plus.
Frontend experience: delivered client side UI using frameworks like React (strongly preferred) or Angular/Vue, with good working knowledge of HTML5, CSS, JavaScript/TypeScript.
Hands-on experience with modern AI workflows: developing agents, working with LLMs, integrating AI capabilities into applications (e.g., prompt engineering, model orchestration)
Experience taking an AI-centric systems into production: build, deploy, monitor, troubleshoot live services, handle performance, scalability, stability.
Familiarity with enterprise-grade practices: version control (Git), CI/CD pipelines, automated testing (unit, integration), code reviews, agile methodologies.
Experience building event-driven or streaming systems (Kafka, Reactor, etc.).
Experience with containerization and orchestration (Docker, Kubernetes) or cloud deployments.
Hands-on developing front-end/back-end interactions in the context of AI workflows (UI for model output, integrations).
Understanding of architecture in enterprise settings: microservices or modular architectures, ability to work within a larger ecosystem of services, dependencies, security and operations concerns.
Excellent problem-solving skills, able to diagnose issues in production systems and propose solutions.
Good communication skills: work across teams (DevOps, QA, product, architecture) and clearly articulate technical trade-offs.
Nice-to-have / differentiators
Implementing retrieval-augmented generation (RAG) systems with vector databases and semantic search
Building multi-modal AI systems integrating text, image, audio, or video processing
Experience with AI safety techniques including constitutional AI, red teaming, and alignment evaluation
Building AI agent frameworks with tool use, planning, and memory capabilities
Implementing human-in-the-loop systems for continuous model improvement and feedback collection
Knowledge of AI governance, model versioning, and experiment tracking in production environments
Building robust prompt engineering frameworks with versioning and A/B
testing capabilities
Experience with LLM observability, monitoring token usage, latency, and quality metrics in production
Implementing guardrails and content filtering for responsible AI deployment
Familiarity with Google's agent/workflow tooling (e.g., Google Actions SDK or other Google-AI tooling).