Software Engineer - Edge AI Systems

 

Palantir builds the world’s leading software for data-driven decisions and operations. By bringing the right data to the people who need it, our platforms empower our partners to develop lifesaving drugs, forecast supply chain disruptions, locate missing children, and more.

We are seeking an experienced Software Engineer to join a newly-formed team focused on developing and deploying advanced AI systems to the tactical edge. This role involves training, evaluating, and deploying LLM agents to edge hardware for interfacing with sensors, effectors, and drone systems. This project is in support of multiple customers in the defense sector that are looking for untethered AI solutions that can be rapidly deployed downrange on hardware with limited capabilities.

As a part of this team, you will build and deploy specialized models and agents that can run on tactical edge hardware, working alongside other experts in AI, LLMs, and systems to shape solutions that redefine complex tactical defense scenarios.

Train and fine-tune edge-capable LLMs for tactical defense applications

Optimize model performance for various edge hardware (GPU, CPU, and specialized accelerator) platforms

Design and implement multi-agent systems for various mission scenarios

Interface LLM agents with sensors, effectors, and drone systems

Benchmark and evaluate agent capabilities, performance, and reliability

Engineer scalable, reliable, and fail-safe systems capable of functioning in high-stakes environments

Proven experience in AI model development, training, and fine-tuning

Experience building LLM agent systems using direct LLM API calls, or frameworks such as LangChain

Experience optimizing AI models and runtime performance for edge hardware

Familiarity with edge AI optimization tools including Ollama, Mojo, TVM, TF Lite, and vLLM

Experience working in the defense sector, especially with weapon and UxV systems, is highly desirable

Ability to manage complexity, optimize for performance, and think critically under pressure

Experience deploying and maintaining robust production systems

5+ years of professional software development experience

2+ years of experience contributing to the system design or architecture (architecture, design patterns, reliability and scaling) of new and existing systems

Experience building and deploying LLMs and LLM agents using modern frameworks such as PyTorch, HuggingFace Transformers, LangChain, and vLLM

Strong proficiency in Rust, Python, or C++

Bachelor's/Master's/PhD in Computer Science, Physics, Mathematics, or related fields

Active US Security clearance or eligibility and willingness to obtain a US Security clearance