Backend Product Engineer
We’re supporting a Series B AI-native company building the next generation of software that helps businesses operate and make decisions with intelligence at the core. Their platform combines large language models, retrieval systems, and workflow automation to ship product experiences that feel fast, reliable, and genuinely useful in day-to-day operations.
We’re looking for an AI Engineer to help build and scale the applied AI layer of the product. You’ll work closely with product and engineering to turn model capabilities into real, production-ready features that users rely on. This is a hands-on role with ownership across everything from prototyping to production systems.
What you’ll do:
• Build and ship LLM-powered product features end to end using prompts, structured outputs, tool use, and function calling
• Design and improve retrieval systems (RAG), including embeddings, chunking strategies, indexing, and semantic search performance
• Build orchestration layers for multi-step AI workflows including agents, tools, memory, retries, and fallbacks
• Integrate AI capabilities into backend services and production infrastructure
• Build evaluation systems to measure quality, latency, cost, and hallucination rates, and iterate to improve reliability
• Partner with product and design to shape AI experiences that are intuitive, fast, and production-ready
• Experiment with new AI models, frameworks, and tooling to improve product capability and performance
What we’re looking for:
• 3+ years building AI-enabled products, backend systems, or ML-powered applications
• Strong hands-on experience with modern LLM APIs (OpenAI, Anthropic, open-source models, etc.)
• Strong Python engineering skills and experience building production backend systems
• Experience working with prompts, structured outputs, and tool-based LLM workflows
• Understanding of retrieval systems, embeddings, vector databases, and semantic search
• Strong product sense with focus on usability, reliability, and performance
• Comfortable working in fast-moving, high-ownership startup environments
Nice to have:
• Experience building agentic systems with tools, planning, and memory
• Familiarity with frameworks like LangChain, LlamaIndex, DSPy, or similar
• Exposure to evaluation pipelines, fine-tuning, or synthetic data generation
• Experience deploying AI systems in cloud environments and monitoring inference in production
• Background in workflow automation, productivity tools, or AI copilots