LLM Engineer

SNI is serving as a trusted IT Outsourcing partner in line with the needs of World's most prestigious firms and carried out successful projects worldwide. Scope: • Design and implement end-to-end Generative AI solutions using Python • Build agentic AI systems and workflows using frameworks such as LangGraph, tool/function calling, MCP, and multi-agent orchestration • Develop advanced RAG pipelines (ingestion, chunking, embeddings, vector search, re-ranking, grounding validation) • Implement memory architectures (short-term, long-term, summarised, and vector-based memory) • Integrate, evaluate, and optimize multiple LLMs (e.g., GPT-4.x, GPT-4o) • Build structured output and tool-calling systems with schema validation • Design evaluation frameworks for hallucination detection, quality scoring, latency, and cost efficiency • Implement Responsible AI guardrails, including input/output filtering and fallback mechanisms • Collaborate with DevOps / LLMOps teams for deployment, monitoring, scaling, and cost optimization Skills: • Strong hands-on Python development (mandatory) • Experience with GenAI frameworks such as LangChain, LangGraph, and CrewAI • Deep understanding of agentic AI systems, orchestration, and tool integration • Experience with Azure AI Foundry and Azure OpenAI Service • Familiarity with vector databases (Azure AI Search, Pinecone, Weaviate, OpenSearch) • Understanding of tokenization, context windows, rate limits, and LLM cost optimization • Experience with API integration, asynchronous programming, and resilient system design • Strong knowledge of Responsible AI principles and risk mitigation techniques Follow us on Linkedin! http://linkedin.com/company/snisourcing/