Senior GenAI Application Analyst (Contract)

Job DescriptionBuild and improve GenAI applications using frameworks such as LangGraph, LangChain or similar orchestration tools.Work with open-weight models, hosted LLMs and model serving patterns.Develop agentic workflows, retrieval-augmented generation, tool calling and prompt orchestration.Integrate GenAI applications with enterprise systems, APIs, data sources and operational platforms.Engineering solutions for production quality, including logging, tracing, evaluation, fallback behaviour and troubleshooting.Requirements5 or more years of software engineering experience, preferably with recent hands-on experience in GenAI application development.Proven experience building production-grade GenAI applications, not only prototypes, experiments or demos.Strong hands on experience with LangGraph, LangChain or similar orchestration frameworks.Practical understanding of RAG, agentic workflows, tool calling, prompt orchestration and context management.Experience integrating LLMs into real applications using APIs, backend services and enterprise data sources.Experience with open-weight models or strong interest backed by hands-on experimentation.Strong backend engineering skills using Python, Java or similar languages.Good understanding of API design, distributed systems and production resilience patterns.Experience with observability, logging, tracing and troubleshooting for GenAI or backend applications. Familiarity with containerised deployment environments such as Kubernetes or OpenShift.Ability to write clean, maintainable and testable code.Strong analytical, debugging and troubleshooting skills.High ownership, high curiosity and genuine interest in building useful AI products.Nice to HaveExperience with DeepAgent or similar agent frameworks.Experience with Langfuse, Elastic or similar observability and search tools.Experience with Redis for caching, conversation state, rate limiting, queue-backed workflows or low-latency GenAI application patterns.Experience with vLLM or similar inference serving frameworks for running Openweight models.Experienced in deploying GenAI workloads on cloud or container platforms.