GenAI Full Stack Developer (PL854)

Paralucent is seeking a GenAI Full Stack Developer to design, build, and scale enterprise AI applications powered by Large Language Models and Azure-native cloud services. The role involves collaborating with various teams to deliver secure and reliable AI-powered applications while focusing on performance and maintainability.

Responsibilities:

• Build and maintain modern web applications using React, Next.js, Angular, or similar frameworks
• Design and develop scalable backend APIs and AI orchestration services using advanced Python, FastAPI, Node.js, Java, or .NET
• Develop cloud-native and serverless applications using Azure services such as Azure Functions, API Management, Logic Apps, and Azure Service Bus
• Implement secure authentication and authorisation systems including OAuth2, OpenID Connect, JWT, and RBAC
• Apply software engineering best practices including testing, CI/CD, documentation, code reviews, and modular architecture
• Design and implement AI-powered capabilities such as assistants, semantic search, summarisation, workflow automation, and intelligent retrieval systems
• Build and optimise enterprise-grade RAG architectures including ingestion pipelines, chunking strategies, embeddings, vector search, hybrid retrieval, reranking, grounding, and hallucination mitigation
• Integrate with LLM providers and orchestration frameworks including Azure OpenAI, OpenAI, Anthropic, Hugging Face, LangChain, Semantic Kernel, or LlamaIndex
• Develop prompt engineering strategies, tool/function calling workflows, guardrails, moderation pipelines, and output validation systems
• Implement observability and evaluation mechanisms for monitoring LLM quality, latency, and reliability
• Integrate AI applications with enterprise systems such as SharePoint, Salesforce, ServiceNow, and internal APIs
• Develop data ingestion, enrichment, transformation, and retrieval pipelines
• Work with relational, NoSQL, and vector databases including PostgreSQL, Redis, Azure AI Search, Pinecone, Elasticsearch, or similar technologies
• Ensure strong governance, privacy, and security controls for enterprise and sensitive data
• Optimise LLM performance, scalability, latency, and operational cost through caching, batching, streaming, and token optimisation
• Design resilient distributed systems using retries, fallbacks, circuit breakers, and graceful degradation patterns
• Implement logging, monitoring, tracing, and observability solutions using OpenTelemetry, Application Insights, Grafana, or similar tooling
• Apply responsible AI principles including privacy controls, auditability, bias mitigation, and secure AI implementation practices
• Participate in system design discussions and contribute to scalable cloud architecture decisions