ML Engineer – Agents, LLMs

This is a fully remote position, open to applicants in Greece.

📋 Description

• Conduct post-training experiments utilizing supervised fine-tuning, preference optimization, reinforcement learning, or other appropriate techniques

• Enhance the planning, tool utilization, execution management, and error recovery processes of agents

• Develop benchmarks, verifiers, and diagnostic tools to assess agent performance and pinpoint failures

• Create and curate training datasets, including agent trajectories and challenging cases derived from target workflows

• Assess and enhance long-context behavior, memory and retrieval interactions, and reliability across multi-step tasks

• Collaborate with ML, Product, and Engineering teams to optimize inference and transition successful experiments into production with definitive regression checks

⛳️ Requirements

• Over 3 years of pertinent ML or research engineering experience, demonstrating clear technical ownership and quantifiable results

• Practical experience with LLM post-training in at least one domain: supervised fine-tuning, preference optimization, reinforcement learning, or a similar approach

• Proven experience in constructing agent systems that involve tool usage, multi-step execution, and error recovery

• Proficient in model and agent evaluation, failure analysis, and the creation or curation of training data

• Strong proficiency in Python, hands-on experience with PyTorch, JAX, TensorFlow, or an equivalent framework, and solid software engineering capabilities

• Experience in enhancing or deploying model-driven systems, with insights into LLM inference performance and cost

• Background in reward modeling or verifier-based training

• Knowledge of long-context training, memory systems, retrieval, or context compression

• Familiarity with distributed training or high-performance LLM serving

• Experience in delivering agents for complex enterprise, coding, or research workflows

🏝️ Benefits

• Competitive compensation package aligned with talent benchmarks

• Hands-on opportunities to shape AI capabilities for Kiefer Tech’s products and real-world applications

• Engineering-focused, high autonomy, low bureaucracy environment that allows you to influence meaningful AI products