AI Engineer
Role in brief
Chaos Labs is looking for a Senior AI Engineer to develop and implement agentic AI systems for financial products. This role involves building multi-agent systems, integrating LLMs, and optimizing performance from prototype to production. Candidates with strong Python skills and experience in agentic architectures and LLM evaluation pipelines should apply.
About the role
This Senior AI Engineer role focuses on creating and refining agentic systems for financial AI products. The work involves designing and building single and multi-agent frameworks that incorporate planning, memory, and tool utilization. A key part of the job is developing workflows using frameworks like LangGraph and integrating Large Language Models (LLMs) through SDKs, managing prompts, structured outputs, and tool calls.
The position also requires building and operating MCP servers with secure schemas and permissions. Success in this role means defining and executing LLM evaluations to assess quality, correctness, latency, cost, and regressions. It also includes optimizing system performance and cost efficiency as solutions move from initial prototypes to full production environments.
The engineer will contribute to establishing best practices for agentic systems and will be responsible for building observability and reliability infrastructure, such as logging, tracing, retries, and state management. This role is part of a team that provides risk management systems, analytics, and an AI platform for major protocols and exchanges, making contributions critical to maintaining industry standards in on-chain risk management.
The annual salary for this role ranges from $149,500 to $212,500.
Skills that matter here
- Python: This role requires strong Python skills for developing and implementing AI systems and API designs.
- API design: The engineer will use API design skills to integrate various components within the AI systems.
- LangGraph: Experience with LangGraph or similar frameworks is necessary for developing agentic workflows.
- MCP servers: The role involves building and operating MCP servers, ensuring secure schemas and permissions.
- LLMs: The engineer will integrate LLMs via SDKs, managing prompts, structured outputs, and tool calling.
Who this role suits
- A senior software engineer with over five years of experience, including at least two years in production AI/ML systems.
- Someone who has practical experience with agentic architectures and tool calling.
- An individual familiar with designing and operating LLM evaluation pipelines.
- A person capable of mentoring others and establishing best practices in agentic systems.
From the employer
- Design and build single and multi-agent systems with planning, memory, and tool use
- Build and operate MCP servers with secure schemas and permissions
- Develop agentic workflows using LangGraph or equivalent frameworks
- Integrate LLMs via SDKs; manage prompts, structured outputs, and tool calling
- Define and run LLM evaluations for quality, correctness, latency, cost, and regressions
- Build observability and reliability infrastructure: logging, tracing, retries, state management
- Optimize performance and cost from prototype to production
- Mentor engineers and establish agentic best practices
- 5+ years software engineering; 2+ years building production AI/ML systems
- Hands-on experience with agentic architectures and tool calling
- Practical experience with MCP servers
- Experience with LangGraph or equivalent agentic frameworks
- Experience designing and operating LLM evaluation pipelines
- Strong Python and API design skills
- Familiarity with RAG pipelines, vector databases, and embedding-based retrieval
- Competitive compensation & equity package
- Career growth opportunities in a rapidly expanding, global technology company
- 21 vacation days + 7 sick days + 8 observed U.S. company holidays
- 100% employer-paid health coverage options for you and your dependents
- FSA / HSA options depending on selected health insurance plan
- Parental leave policy
- Wellness programs including OneMedical, Teladoc, Talkspace, and EAP
- Pre-tax commuter benefits
Questions about this role
What is the remote work policy for this position?
This is a fully remote position.
What is the seniority level for this role?
This is a senior-level position, requiring 5+ years of software engineering experience and 2+ years building production AI/ML systems.
What skills are required for this role?
Key skills include Python, API design, LangGraph or equivalent agentic frameworks, MCP servers, and experience with LLMs and LLM evaluation pipelines.