Forward Deployed Engineer - LLM Post-training
Reflection6 months ago
San Francisco, CA, USA or New York, NY, USAMid Level
H1B sponsor
Responsibilities
- Fine-tune open-weight models for customer-specific use cases by preparing datasets, configuring training runs, and iterating based on evaluations
- Build and maintain evaluation infrastructure, including evaluation suites, test sets, baselines, and improvement measurements
- Clean, format, and assess raw customer data while identifying adversarial or noisy samples
- Build reproducible data pipelines for training data
- Debug training and inference issues by interpreting loss curves and training dynamics
- Support deployment of fine-tuned models across public cloud, VPC, and on-premises environments
- Help ensure inference performance and reliability in production
- Develop fine-tuning playbooks, evaluation benchmarks, and best practices
- Collaborate with customers and research teams to translate requirements and advance model capabilities
Requirements
- Hands-on experience fine-tuning language models, including preparing datasets, running training loops, evaluating results, and shipping a fine-tuned model
- Familiarity with supervised fine-tuning, preference optimization, reinforcement fine-tuning, DPO, RLHF, or similar techniques
- Understanding of evaluation methodology, training graphs, benchmark overfitting, and model improvement measurement
- Comfort working with GPUs, compute management, and debugging training failures
- Strong Python software engineering fundamentals and experience writing clean, reproducible code
- Experience with data pipelines and version control for datasets and experiments
- At least 3 years of engineering experience with meaningful exposure to applied ML or ML engineering
- Ability and interest to work directly with customers, understand user needs, and translate domain requirements into training strategies
- Self-starter with strong ownership who can work effectively in a fast-paced startup environment
Benefits
- Comprehensive medical, dental, vision, life, and disability insurance
- Fully paid parental leave for all new parents, including adoptive and surrogate journeys
- Financial support for family planning
- Paid time off
- Relocation support
- Daily lunch and dinner provided
- Regular off-sites and team celebrations
- Salary and equity compensation are offered, but amounts are not specified
Tech Stack
Categories
Forward DeployedML Engineering
About Reflection
Reflection is a New York–based, privately held research lab developing open foundational AI models and agentic coding tools for developers, enterprises, and public-sector users. The team includes former researchers from DeepMind, OpenAI, and Anthropic, and their work focuses on transparent, customizable systems that organizations can deploy with ownership and control.