Reflection is hiring a Forward Deployed Engineer for LLM post-training who fine-tunes open-weight language models for customer use cases — preparing and pipelining datasets, configuring and debugging training runs, building evaluation infrastructure, and deploying models across hybrid environments. Core stack: Python, GPU compute, and techniques like SFT, DPO, and RLHF.
You will prepare customer datasets, run language-model fine-tuning workflows, build evaluation infrastructure, and diagnose training issues. You will deploy adapted models across hybrid environments and translate customer requirements into training strategies.
Responsibilities
Fine-tune open-weight models for customer-specific use cases
Prepare datasets and configure training runs
Build and maintain evaluation infrastructure
Prepare, clean, format, and pipeline customer training data
Debug training and inference issues
Support deployments of fine-tuned models across hybrid environments
Contribute to fine-tuning and evaluation playbooks and benchmarks
Requirements
Applied ML experience fine-tuning language models
Familiarity with SFT, DPO, RLHF, or similar techniques
Understanding of evaluation methodology and training graphs
Experience with GPUs, compute management, and training debugging
Software engineering fundamentals in Python
Experience with data pipelines and version control for datasets and experiments
3+ years of engineering experience with applied ML or ML engineering
Customer-facing experience translating domain requirements into training strategies
Benefits
Stock options
Comprehensive medical, dental, vision, and life insurance
Annual wellness allowance
Daily office lunch and dinner
22 weeks of paid parental leave
Unlimited paid time off in the U.S.
30 days of vacation in the U.K.
Visa sponsorship support
Regular off-sites, happy hours, and team celebrations