Software Engineer, Agents

Harvey

. Build systems that make AI agents indispensable to legal professionals .

Posted 10/27/2026full-timeSan Francisco • California • United StatesJuniorMid-Level💰 $161,300 - $241,900 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building domain-specific AI agents, with a strong focus on Python programming, LLM APIs, and agent frameworks. Capable of optimizing agent performance through prompt engineering and effective evaluation strategies.

Highest-signal resume keywords

Python ProficiencyExperience With LLM APIsAgent Frameworks ExpertiseUser-Facing Product DevelopmentIterative Mindset

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Software EngineeringPrompt EngineeringModel SelectionTool DesignContext-Window ManagementEval-Harness DevelopmentCaching StrategiesParallel Tool CallsSubagent PatternsPerformance Optimization

Soft Skills

AdaptabilityHumilityDecision-MakingCollaboration

Industry Keywords

AI AgentsLegal WorkflowsAgentic SystemsObservabilityInstrumentation

Tech Stack

Tools & technologies

Python

About the role

Key responsibilities & impact

Build systems that make AI agents indispensable to legal professionals
Design environments and actions for agentic professional work
Make model selection decisions and manage context windows
Create optimal tools and develop evaluations to enable faster iteration
Partner with customers and PMs to understand legal workflows
Design practical evaluations defining excellent performance and ship effective agents
Optimize agent performance through prompt engineering, model selection, tool design, skill writing, context-window management, and eval-harness development
Design and implement low-latency agent-execution infrastructure with the model infrastructure team
Develop caching strategies, parallel tool calls, and subagent patterns
Improve observability and instrumentation to profile agent behavior and identify bottlenecks
Stay current on developments in agentic systems and apply learnings to products

Requirements

What you’ll need

2–5 years of software engineering experience post-BS/MS
Passion for building effective domain-specific agents
Iterative mindset; ability to develop proof of concepts, make decisions quickly, and ship v0s
Comfortable using evaluations to drive quality
Humble and adaptable about code and frameworks
Proficiency in Python
Experience working with LLM APIs and agent frameworks
Experience shipping user-facing products on the backend or full-stack
Ability to work from the San Francisco office 3 days per week
Legal authorization to work in the country where the role is located
Willingness to relocate if not currently based in San Francisco

Benefits

Comp & perks

Opportunity for personal, professional, and financial growth
Reasonable accommodations for applicants with disabilities
Equal opportunity employment and nondiscrimination