ML Engineer – Agents, LLMs

• Run post-training experiments using supervised fine-tuning, preference optimization, reinforcement learning, or other suitable methods
• Improve how agents plan, use tools, manage execution, and recover from errors
• Build benchmarks, verifiers, and diagnostic tools to measure agent performance and identify failures
• Generate and curate training data, including agent trajectories and difficult cases from target workflows
• Evaluate and improve long-context behavior, memory and retrieval interactions, and reliability over multi-step tasks
• Work with ML, Product, and Engineering to improve inference and bring successful experiments into production with clear regression checks

• 3+ years of relevant ML or research engineering experience, with clear technical ownership and measurable results
• Hands-on LLM post-training experience in at least one area: supervised fine-tuning, preference optimization, reinforcement learning, or a comparable method
• Experience building agent systems involving tool use, multi-step execution, and error recovery
• Strong skills in model and agent evaluation, failure analysis, and the creation or curation of training data
• Strong Python, hands-on experience with PyTorch, JAX, TensorFlow, or a similar framework, and solid software engineering skills
• Experience improving or deploying model-backed systems, with an understanding of LLM inference performance and cost
• Reward modeling or verifier-based training
• Long-context training, memory systems, retrieval, or context compression
• Distributed training or high-performance LLM serving
• Experience delivering agents for complex enterprise, coding, or research workflows

• Competitive package aligned with talent benchmarks
• Hands-on work shaping AI capabilities for Kiefer Tech’s products and real-world applications
• Engineering-first, high autonomy, low bureaucracy, and space to shape meaningful AI products