Engineering Manager - Forward Deployed Engineering (LLM)

Baseten powers mission-critical inference for the world's most dynamic AI companies, and they are seeking an Engineering Manager to lead and mentor a team of Forward Deployed Engineers. This role involves both hands-on technical ownership and managerial leadership to optimize LLM inference workloads and ensure high performance in production environments. Responsibilities: Lead, mentor, and grow a team of Forward Deployed Engineers, providing guidance on technical direction, project execution, and professional development; Set clear goals and ensure timely, high-quality delivery across multiple customer-facing projects involving LLM deployment and inference optimization; Collaborate with leadership to align team priorities with company and customer goals, balancing short-term delivery, widely varying customer priorities, and long-term technical initiatives; Player-coach – While much of this role will be leading the team, you will also be expected to be a key driver on strategic product initiatives and customer engagements; Develop and maintain software systems and product features using one or more general-purpose programming languages in a production-level environment, with a preference for Python due to its relevance in ML projects; Drive customer impact by designing, implementing, and deploying Baseten solutions end-to-end (problem framing → evaluation → production deployment → monitoring); Deliver with velocity: turn vague objectives into clear specs and well-defined PoCs so we can rapidly ship well-tested services and outcomes for our customers; Optimize and enhance AI/ML projects, contributing to the continuous improvement of our technical stack; Own products and customer projects end-to-end, functioning as both an engineer, project manager, and product manager, with a focus on user empathy, project specification, and end-to-end execution Qualifications: Bachelor's, Master's, or Ph.D. in Computer Science, Engineering, or related field; 4+ years of professional software engineering experience, including 1+ year in a leadership or mentorship capacity; Strong programming skills in Python, with production experience in building or optimizing ML inference systems; Proven experience with LLMs, inference optimization, or serving frameworks (e.g., vLLM, TensorRT, Triton, Hugging Face, Ray Serve); Familiarity with observability, profiling, and cost/performance tradeoffs in production ML systems; Excellent communication and collaboration skills—able to lead cross-functional efforts and drive outcomes in ambiguous, fast-paced environments Required Skills: Python, Machine Learning Inference Systems, Large Language Models (LLMs), Inference Optimization, Serving Frameworks, Profiling, Cost/Performance Tradeoff Analysis, GPU Infrastructure, Distributed Inference, Model Compression Techniques