AI Agent Engineer
location_on24;26, Caselli Avenue, Castro District, San Francisco, California, 94114, United States
Job Description
About TRM and the AI Engineering Team
TRM is a blockchain intelligence company on a mission to build a safer world for billions of people. We are a lean, high-impact team tackling some of the world’s most critical challenges, ranging from human trafficking and financial fraud to terrorist financing. We power governments, financial institutions, and crypto companies when the clock is running and the consequences are real. Every TRMer is a bet on our future and has the power to change our trajectory.
The AI Engineering Team is chartered with enabling next-generation AI applications, with a special focus on Large Language Models (LLMs) and agentic systems. Our mission is to build robust pipelines, high-performance infrastructure, and operational tooling that allow AI systems to be deployed with speed, safety, and scale. We manage petabyte-scale pipelines, serve models with millisecond-level latency, and provide the observability and governance needed to make AI production-ready. We are also deeply involved in evaluating and integrating cutting-edge tools in the LLM and agent space—including open-source stacks, vector databases, evaluation frameworks, and orchestration tools—to unlock TRM’s ability to innovate faster than the market.
The Role and Impact
As an AI Agent Engineer, you will architect and implement a robust agentic framework that supports tool use, context retrieval, memory, and planning. You will build intelligent, modular agents that automate investigative tasks and augment analyst decision-making. This role involves extending and scaling our LLM infrastructure, including prompt engineering, RAG, and evaluation loops, while designing safe, observable, and auditable agent behaviors to ensure reliability in high-sensitivity environments.
You will evaluate performance across metrics like reasoning, latency, success rate, and hallucination, iterating based on user feedback and system telemetry. This position contributes to a culture of high ownership, rapid experimentation, and ethical AI deployment.
About the Team and Culture
The AI Engineering team operates with a high level of collaboration and interdependence, fostering an inclusive culture where connections extend beyond work. We value diverse personalities and seek someone who is both results-driven and sociable, with strong communication, leadership, and teamwork skills, along with a positive, solutions-oriented mindset.
As a globally distributed team, members may observe different timezones. However, most of the team will overlap between the hours of 7am-12pm PST for meetings and collaboration. All team members, regardless of location, must have at least a 4-hour overlap with PST business hours.
Life at TRM
We build to protect civilization. That promise shows up in how we work every day. TRM runs fast. Really fast. We’re a high-velocity team that expects ownership, clarity, and follow-through. People who thrive here are inspired by hard problems, experimentation, and direct feedback. If it takes months elsewhere, it often ships here in days. If you are optimizing primarily for consistent work-life balance, use the interview process to pressure-test fit. We want teammates who thrive here, not just survive here.
We coach directly, assume positive intent, and play for the front of the jersey. Our core values include:
- Impact-Oriented Trailblazer: We put customers first, driving for speed, focus, and adaptability.
- Master Craftsperson: We prioritize speed, high standards, and distributed ownership.
- Inspiring Colleague: We value humility, candor, and a one-team mindset.
What You’ll Do Here
This work has teeth. At TRM, your week might include driving critical investigations that can’t wait for typical business hours, shipping products in days when others would schedule quarters, and partnering with teams across time zones to deliver insights while the story is still unfolding. You will build new solutions from first principles when the playbook doesn’t yet exist, protecting victims and customers by tracing illicit activity and disrupting criminal networks.
Join Our Mission
We look for people who want their work to matter, who build with speed and rigor, and who take pride in protecting others through their craft. If you’re excited by TRM’s mission but don’t check every box, apply anyway. We hire for slope, judgment, and the will to learn fast.
Build to protect civilization. Let’s do it together.
Work location
Work model: On-site
24;26, Caselli Avenue, Castro District, San Francisco, California, 94114, United States
San Francisco, California
Key Responsibilities
- check_circleExtend and scale LLM infrastructure including prompt engineering, RAG, and evaluation loops
- check_circleEvaluate agent performance across metrics like reasoning, latency, success rate, and hallucination
- check_circleIterate on system improvements based on user feedback and system telemetry data
- check_circleArchitect and implement a robust agentic framework supporting tool use, context retrieval, memory, and planning
- check_circleBuild intelligent, modular agents to automate investigative tasks and augment analyst decision-making
- check_circleDesign safe, observable, and auditable agent behaviors to ensure reliability in high-sensitivity environments
Requirements
- verifiedStrong engineering background with deep experience in backend or systems work (Python preferred)
- verifiedHands-on experience building with LLMs, agents, and tooling frameworks (LangChain, semantic caches, vector DBs, etc.)
- verifiedComfort working with agentic pipelines and optimizing information flow into AI systems
- verifiedThoughtful approach to system design, with an eye for safety, scalability, and explainability
- verifiedHigh product empathy - you care about how agents impact real users (analysts) and optimize accordingly
- verifiedBias toward experimentation and iteration - you’re excited to try, learn, and ship fast
- verifiedPrevious experience with knowledge graphs, task orchestration, or AI safety a plus
- verifiedStrong communication, leadership, and teamwork skills
- verifiedPositive, solutions-oriented mindset
- verifiedAt least 4 hour overlap with PST business hours