SILQFi

The Role We're looking for a Generative AI Engineer who builds production-ready AI systems. You understand LLM orchestration, agentic workflows, and how to architect solutions that scale. What You'll Do ● Design LLM orchestration and agentic AI systems with multi-step reasoning ● Build RAG pipelines with vector databases and semantic search ● Develop AI agents using frameworks like LangGraph, CrewAI, AutoGPT, or custom implementations ● Apply prompt/context engineering and fine-tuning strategies ● Optimize for cost, latency, and reliability in production Technical Requirements ● Strong Python and software engineering fundamentals ● Experience with LLM APIs (Gemini, OpenAI, Anthropic, open-source models) ● Agentic framework experience (LangGraph, LangChain, CrewAI, Semantic Kernel, etc.) ● Hands-on with RAG architectures and vector databases (Pinecone, Weaviate, ChromaDB). Retrieval optimization and embeddings ● Knowledge of prompt/context engineering, few-shot learning, context window management and chain-of-thought techniques ● Fine-tuning (LoRA, full fine-tuning), Multi-agent coordination and orchestration patterns ● Model evaluation and observability (LangSmith, Weights & Biases) What We're Looking For ● You've shipped LLM-powered features to production ● You understand the tradeoffs between different approaches (RAG vs fine-tuning vs prompt engineering vs context engineering) ● You can debug black-box model behaviors ● You stay current with the rapidly evolving various AI platformsGolang, typescript, Python, R, ML