Research Engineer

The role

The Research Engineer will build and scale the post-training stack, including SFT, preference optimization, and reinforcement learning. You will develop memory, context, representation, and data generation machinery to turn hypotheses into models that ship.

What you will do

• Build and scale the post-training stack including SFT, preference optimization, and reinforcement learning
• Build memory and context machinery for long-horizon agents
• Build the representation layer including ontologies and knowledge graphs
• Design and implement data generation and curation pipelines
• Build RL environments including sandboxed landscapes and verification harnesses
• Build and run the offline eval harness for long-horizon agentic behavior
• Run experiments end to end including design, launch, debug, and analysis
• Optimize training and inference throughput
• Take training results from evaluation to serving traffic
• Establish standards for reproducibility, experiment tracking, and result hygiene

Required qualifications

• Significant experience training, fine-tuning, or post-training language models
• RL tuning experience such as RLHF, RLAIF, RLVR, GRPO-family, or agentic RL
• Experience with memory and context for long-running agents
• Strong software engineering fundamentals
• Fluent in Python and PyTorch or JAX
• Ability to design, run, and interpret an experiment with empirical rigor
• Experience working with GPU infrastructure at scale
• Clear written communication skills

Nice to have

• Experience building RL environments, execution sandboxes, or verifiable-reward task suites
• Experience with long-context modeling
• Experience with knowledge graphs, ontologies, or semantic layers over structured enterprise data
• Experience with agent memory systems in production
• Experience with code models
• Contributions to open-source ML systems
• Track record of publications, technical reports, or open-source releases
• An advanced degree in CS, ML, math, physics, or a related quantitative field, or equivalent industry research experience

About the company

Tessera Labs is an AI platform designed as a transformation engine for large enterprises. The company raised a $60M Series A led by Andreessen Horowitz.