AI/ML Engineer

We're seeking a ML/AI Engineer to help us deliver a high quality and performant GenAI agentic solution. This role will be central to designing, implementing and deploying LLM-based reasoning, retrieval-augmented generation, graph representations, and multi-agent orchestration. You'll work closely with founders, engineers and domain experts. Responsibilities: Design and scale retrieval pipelines and agent-based architectures that go beyond standard RAG, including graph knowledge integration and multi-hop reasoning Develop and maintain core infrastructure for prompt orchestration, embedding workflows, and vector search, optimized for performance and fine-grained control Implement robust evaluation harnesses to monitor model accuracy, responsiveness, and consistency across real-world user tasks Fine-tune and adapt LLMs to domain-specific tasks with complex knowledge synthesis Collaborate with backend engineers to integrate GenAI components into production environments with secure interfaces Requirements: 3+ years experience shipping ML systems to production in startup or enterprise settings Strong command of GenAI architectures, including LLMs, RAG pipelines, graph and vector databases, and multi-agent systems Proficient in Python, with experience using PyTorch or TensorFlow in production Familiarity with frameworks like LangChain, Hugging Face Transformer and MLflow Experience deploying ML workloads on cloud infrastructure (AWS or Azure) Ability to balance model performance, latency and observability Comfort working in fast-moving, ambiguity-rich settings where iteration is key