Requirements
The ideal candidate will possess strong Python and general software engineering experience, with hands-on experience developing GenAI/LLM solutions in a production or enterprise environment. Experience with RAG, embeddings, vector/semantic search, enterprise data, agentic AI, tool/function calling, and familiarity with multiple LLM providers are essential. Strong API and enterprise integration skills, along with an understanding of LLM evaluation, guardrails, observability, and AI security, are required. Experience with Docker/Kubernetes and on-premise/private environments is desirable.
Description
ABOUT THE ROLEAI Engineer responsible for designing and delivering GenAI solutions on a bespoke, on-premise AI platform (Arthur). The role will focus on building production-ready AI applications and integrating enterprise systems and data with LLM providers, including Anthropic, OpenAI and Google.RESPONSIBILITIESDesign, develop and productionise GenAI/LLM applications and use cases.Build RAG, agentic AI and tool-enabled workflows using enterprise data and systems.Integrate AI solutions with APIs, databases, applications and external LLM providers.Develop effective prompt and context engineering approaches, including structured outputs and guardrails.Implement testing, LLM evaluation, monitoring and observability to ensure solution quality and reliability.Apply appropriate security, data privacy and Responsible AI controls.Collaborate with architects, platform engineers, business SMEs and other delivery teams.Contribute reusable components, integration patterns and engineering best practices.REQUIREMENTSStrong Python and general software engineering experience.Hands-on experience developing GenAI/LLM solutions in a production or enterprise environment.Experience with RAG, embeddings, vector/semantic search and enterprise data.Experience with agentic AI, tool/function calling and/or MCP.Familiarity with multiple LLM providers such as Anthropic Claude, OpenAI and Google/Gemini.Strong API and enterprise integration skills.Understanding of LLM evaluation, guardrails, observability and AI security.Experience with Docker/Kubernetes and on-premise/private environments is desirable.Strong problem-solving, communication and stakeholder engagement skills.A model-agnostic engineering mindset, with the ability to work across different LLMs rather than being dependent on a specific hyperscalerSoftServe is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment regardless of race, color, religion, age, sex, nationality, disability, sexual orientation, gender identity and expression, veteran status, and other protected characteristics under applicable law.