Senior Research Engineer

Drug development shouldn’t be guesswork, not when patients are waiting.

Pathos is building a next-generation biotech with AI at the core. Not as a feature, but as the operating system for how medicines get developed. We believe most drugs don’t fail because the science was wrong. They fail because they were tested in the wrong patients, with the wrong assumptions, in trials that couldn’t answer the real question: who benefits, and why?

Pathos exists to change that. We’re building the largest foundation model in oncology and pairing it with proprietary AI systems, deep oncology expertise, and 200+ petabytes of multimodal data linked to patient outcomes, so we can make development decisions with more precision, much earlier.

This is not theoretical. We’re well-capitalized and have the leadership to build a generational company. We invest in and advance our own clinical-stage programs, using our AI platform to sharpen trial design, patient selection and biomarker strategy. So therapies reach the patients most likely to benefit, sooner.

How We Build
Pathos does not operate like a traditional biotech. There is no middle management. There are no layers of approval. The company is designed, from the ground up, around small teams of 2–4 subject-matter experts who each command hundreds of AI agents to do the work that used to require dozens of people.

Everyone builds. Everyone ships. Every function at Pathos — from clinical execution to asset selection to the foundation model itself — runs on this model. Our product velocity delivers meaningful outcomes in hours instead of weeks. This is not a future aspiration. It is how we operate today.

The people who thrive here are operators: deep experts who can specify what needs to happen, orchestrate AI agents to execute at scale, and make high-judgment calls that compound over time. If you have spent your career building and shipping AI systems at scale, this is the environment where that experience becomes a superpower.

About the role

We are seeking exceptional Senior Research Engineers to join our mission-critical team building the world's best oncology foundational models. As an AI-driven drug development company, these models are the engine that powers everything we do, from predicting patient survival, to identifying novel therapeutic targets to optimizing clinical trial design.

In this role, you'll be at the intersection of cutting-edge AI research and real-world drug development. You'll work on foundational models that integrate diverse data modalities, known cancer biology, tumor mechanisms, DNA/RNA sequencing, detailed medical notes, and examination results to generate insights that directly inform our clinical-stage programs.

You'll participate in both pre-training and post-training of our foundation models, requiring deep expertise in modern architectures and post-training algorithms such as reinforcement learning. You may also operate at the CUDA level, building customized kernels and understanding performance at the hardware-software interface.

What You'll Do

• Design, implement, and optimize large-scale oncology foundation models integrating genomic sequences, medical notes, lab results, imaging, and clinical outcomes
• Build and experiment with modern architectures optimized for biomedical applications
• Spearhead pre-training and post-training efforts, including RLHF, DPO, RLAIF, and other alignment techniques
• Write and optimize custom CUDA kernels; profile and resolve performance bottlenecks across the hardware-software interface
• Maintain and optimize our 1,000+ H200 GPU cluster for reliability, utilization, and performance
• Build distributed training and inference pipelines, experiment tracking systems, and evaluation frameworks
• Develop benchmarks that measure real progress on drug development-relevant tasks
• Collaborate with oncologists, biologists, and clinical development teams to ground model development in real therapeutic questions
• Contribute to publications in top-tier ML and biomedical venues (NeurIPS, ICML, ICLR, Nature, Cell, etc.)

What We're Looking For

Required

• Ph.D. in Computer Science, Machine Learning, Computational Biology, or a related field, or an M.S. with 5+ years of relevant industry experience
• Publication record in machine learning, including multiple first-author papers at top-tier venues
• 3 to 5 years of hands-on deep learning experience (PyTorch, JAX, or TensorFlow)
• Strong command of modern architectures: Transformers, attention mechanisms, state-space models, mixture-of-experts
• Hands-on experience with post-training techniques: RLHF, DPO, PPO, or similar
• Expert-level GPU programming and CUDA, including custom kernel development and performance profiling
• Practical experience training or fine-tuning large-scale models (multi-billion parameter) in distributed settings (DeepSpeed, FSDP, Megatron, or similar)
• Experience managing GPU clusters and ML infrastructure (Kubernetes, SLURM, or equivalent)
• Strong software engineering fundamentals in Python and C++/CUDA
• Clear communicator, able to present complex technical work to both engineering and scientific audiences

Preferred

• Background in oncology, cancer biology, or drug development
• Experience with biomedical foundation models (AlphaGenome, GeneFormer, Evo2, etc.)
• Deep knowledge of cancer genomics, tumor biology, or mechanisms of resistance
• Contributions to ML systems frameworks (FlashAttention, Triton, xFormers, etc.)
• Experience with multi-modal learning and cross-modal architectures
• Familiarity with advanced training techniques: synthetic data generation, curriculum learning, data filtering
• Familiarity with regulatory considerations in healthcare AI (FDA, HIPAA, GxP)
• Open-source contributions to ML projects or frameworks

Location

This is a hybrid role, requiring up to 3-4 days per week onsite, in our NYC Headquarters.

[{'location': 'New York Office', 'currency': 'USD', 'frequency': 'YEAR', 'rangeStart': 180000.0, 'rangeEnd': 200000.0, 'isRemote': False}]