Bonfy.AI is building the trust layer for generative AI. Our Adaptive Content Security platform detects and mitigates subtle risks embedded in large language model (LLM) outputs before they reach users. From hallucinations to hidden data leaks, we enable enterprises to deploy GenAI confidently, without compromising truth, privacy, or reputation.

We are model-agnostic, outcome-driven, and unapologetically rigorous. Our customers include leading Fortune 500 teams working in high-stakes sectors where trust is not optional.

Why This Role Matters

We need an MLOps Engineer to optimize our GPU-accelerated ML infrastructure for performance and cost efficiency. Working with our existing Sr. DevOps and Sr. SRE teams, you'll focus on the specialized ML optimization challenges that require deep machine learning expertise.

• GPU & Cost Optimization: Design optimal GPU configurations and ML deployment strategies to maximize performance while minimizing cloud costs.
• ML Performance Tuning: Optimize model serving, memory management, and inference pipelines for production LLM workloads. You will also work with models and customize prompts, write pre- and post-processing methods to improve accuracy and speed (production coded), and implement new models functionality in the system.
• DevOps Collaboration: Work with our Sr. DevOps/SRE teams to implement ML-specific solutions and monitoring

What We're Looking For

• ML Infrastructure Optimization: 5+ years optimizing production ML systems with focus on GPU utilization and cost management
• GPU & LLM Expertise: Deep understanding of GPU architectures, memory management, and LLM inference optimization
• Python + DevOps Integration: Expert Python programming with experience working alongside DevOps/SRE teams on ML-specific solutions
• Bonus: Experience at GPU-focused ML companies (SambaNova, NVIDIA, etc.) or with high-performance ML serving frameworks

Why Join Us

• Collaborative Impact: Work with our existing Sr. DevOps and Sr. SRE teams to solve ML-specific challenges that require specialized expertise
• Technical Depth: Focus purely on cutting-edge ML optimization problems without getting pulled into general infrastructure work
• High Autonomy: Direct collaboration with engineering leadership in a fast-paced, technically rigorous environment
• Competitive Package: Strong salary, equity, comprehensive benefits, and flexible hybrid work model
  
  Bonfy.AI — Truth. Security. Intelligence.