Research Engineer

Pramaana Labs • Palo Alto, CA

2d

About The Position

Pramaana Labs is a frontier AI lab building a verification layer for AI. Founded in 2025 and headquartered in Palo Alto, the company turns complex human knowledge—including tax codes, legal rules, clinical guidelines, and security protocols—into formal representations that make AI answers traceable, challengeable, and provable. Its architecture combines foundation models trained to formalize and reason with a symbolic world model encoded in Lean 4. The company was founded by a team from Google, DeepMind, and Glean, bringing together frontier AI researchers and formal methods experts.

The Research Engineer will build and improve systems that turn complex knowledge into formal representations and use those representations to reason and prove. Working closely with researchers and formal methods engineers, the role contributes to the domain formalizer, autoformalizer, and prover, improving their accuracy, repeatability, and efficiency.

This hands-on role combines software engineering with careful experimentation. Work may include model and tool orchestration, evaluation improvements, data pipelines and training environments, and new representations. The engineer will own a focused workstream based on their strengths and team needs, with opportunities to contribute across the research stack. They will take ideas from initial experiments through tested implementations, investigate failures, and measure changes in correctness, coverage, latency, and cost.

Requirements

• Strong software engineering fundamentals and hands-on experience building large-scale ML systems, research infrastructure, or high-performance training pipelines.
• Experience training or post-training large foundation models, including distributed training, fine-tuning, reinforcement learning, and large-scale experimentation.
• Deep proficiency in Python and modern ML frameworks such as PyTorch, JAX, DeepSpeed, FSDP, Megatron-LM, or equivalent distributed training and inference infrastructure.
• Experience building agentic AI systems, including tool use, multi-step reasoning, agent orchestration, and evaluation of complex model behaviors.
• Familiarity with modern post-training techniques, including supervised fine-tuning, reinforcement learning, preference optimization, synthetic data generation, and reasoning-focused training.
• Strong research and experimental judgment, including experience designing benchmarks, running ablation studies, analyzing model failures, and translating research ideas into measurable improvements.
• Ability to operate independently at the intersection of research and engineering, rapidly prototyping ideas and scaling successful experiments into robust systems.
• Strong engineering, careful experimentation, and curiosity to learn how models and formal systems work together; prior formal verification experience is not required.

Nice To Haves

• Experience building autoformalization, theorem-proving, or other systems that combine models with symbolic tools.
• Experience with Lean, Coq, Isabelle, SMT solvers, compilers, or program analysis.
• Experience optimizing model inference, parallel workloads, or evaluation pipelines for speed and cost.
• Substantial research code, open-source contributions, or projects demonstrating strong engineering and experimental work.

Responsibilities

• Build next-generation neuro-symbolic AI systems at the intersection of foundation models, formal methods, automated reasoning, and verification.
• Design evaluation frameworks and research benchmarks to study reasoning capabilities, generalization, robustness, and computational efficiency.
• Develop post-training and data-synthesis pipelines, exploring synthetic data generation, reinforcement learning, and model self-improvement.
• Research and implement approaches to knowledge representation, compositional reasoning, program synthesis, and constraint-based inference for complex real-world domains.
• Drive end-to-end research and engineering, from rapid prototyping and controlled experimentation to ablation studies, performance optimization, and scalable production systems.
• Build and improve the domain formalizer, autoformalizer, and prover, including work on model and tool orchestration, evaluation, data pipelines, training environments, and representations.
• Investigate system failures and measure whether changes improve correctness, coverage, latency, and cost.

What This Job Offers

• Job Type: Full-time
• Education Level: No Education Listed