SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Certa is an AI-first third-party operating system used by Fortune 500 companies and fast-growing startups to onboard, assess, and monitor vendors, suppliers, and partners across risk, compliance, and ESG. The company has processed over 10 million entities for 100,000+ users across 120+ countries and is backed by Fin Capital, Vertex Ventures, and Point72 Ventures.
As an AI Engineer, you will design and ship generative AI and LLM-powered services that deliver intelligent features to the enterprise platform. Your responsibilities include:
- Design, develop, and deploy AI-driven solutions from prototype to production, including intelligent chatbots, AI-driven recommendations, and workflow automation.
- Build and optimize end-to-end RAG (Retrieval-Augmented Generation) pipelines, handling data ingestion, parsing, chunking, vector indexing, and prompt engineering.
- Develop and refine LLM-based agentic systems for complex multi-step tasks, incorporating planning, memory, and tool use.
- Rigorously evaluate models and pipelines on accuracy, latency, and hallucination rates, using testing and user feedback to iterate.
- Write clean, maintainable, testable code with strong monitoring and logging to ensure AI components are scalable and fit the overall system architecture.
- Collaborate with product, design, and engineering teams to integrate AI seamlessly into products, mentor teammates on generative AI best practices, and explore new AI advancements.
Required qualifications include 5+ years of backend engineering with expert Python skills, scalable API/service design, and AWS deployment experience. You need proven experience building real products on LLMs and generative AI, with hands-on RAG and agent work. Strong applied AI depth is essential: prompt design, function calling, tool use, context-window management, and understanding of embeddings, tokenization, vector search, and transformers. You should be hands-on with LLM orchestration libraries (LangChain, LlamaIndex) and vector databases (Pinecone, Chroma, Milvus). Cloud and DevOps expertise is required, including productionizing LLM/RAG services on AWS with infrastructure-as-code, observability, security, and progressive delivery. Excellent communication skills and a self-directed approach to troubleshooting are essential. Nice-to-have qualifications include enterprise B2B SaaS experience, full-stack/frontend depth, complex multi-agent or multi-modal AI, early-stage startup experience, and active involvement in the AI community.
