Engineer - HelloCounsel.ai

Company Overview

Not specified.

Job Summary

As an Engineer at HelloCounsel.ai, you will be responsible for developing and deploying autonomous AI agents tailored for US personal injury law firms. Your work will directly impact how legal firms manage cases by creating reliable, end-to-end AI systems that handle tasks such as client onboarding, document retrieval, claim processing, and case progression. You will own a specific workstream, ensuring the agent operates seamlessly across various case management systems, adapts to custom firm processes, and maintains high reliability and quality standards.

Responsibilities

• Design, develop, and deploy production-level Large Language Model (LLM) agents capable of operating autonomously for weeks, including managing state, memory, retries, escalation, and recovery.
• Build and maintain integration layers that abstract diverse legal case management platforms (e.g., Clio, Filevine, Litify, MyCase) into a unified, reliable interface.
• Establish and enforce reliability disciplines through comprehensive evals, transcript regression suites, and edge-case testing to ensure 95%+ performance consistency.
• Continuously improve the agent’s conversational quality, analyzing transcripts and refining the agent’s voice and interaction style to meet high standards.
• Develop streamlined onboarding processes for new law firms, accommodating their unique intake forms, processes, and CMS configurations within days.
• Collaborate directly with customers, founders, and a small, autonomous team to iterate on product features, troubleshoot issues, and enhance agent performance.

Qualifications

• Proven experience shipping production LLM agents used by real users, with a track record of handling real failures and implementing fixes.
• Strong understanding of agent reliability engineering, including writing evals, regression tests, and handling edge cases.
• Experience normalizing and integrating messy third-party systems, such as APIs with poor documentation, legacy platforms, and custom configurations.
• Excellent product instincts with the ability to identify conversational flaws and prioritize fixes that improve user experience.
• High standards for quality and reliability, with a disciplined approach to testing and evaluation.
• Strong communication skills to work directly with customers and cross-functional teams.
• Educational background: Not specified, but relevant experience and skills are prioritized.

Preferred Skills

• Experience working in legal tech or case management systems.
• Familiarity with building scalable integration layers similar to Plaid’s approach for banking.
• Open-source contributions or side projects related to AI agents or automation.
• Ability to work in a fast-paced, deadline-driven environment with minimal supervision.

Experience

• Approximately 5 years or less of relevant experience.
• Experience in building and deploying autonomous AI agents in production environments.
• Proven track record of managing systems where errors have tangible impacts, such as agents, payments, or pipelines.

Environment

• Location: Bangalore or willing to relocate.
• Work setting: In-office, with a strong emphasis on in-person collaboration.
• Work hours: Overlap with US working hours, including late evenings.
• Culture: Fast-paced, deadline-driven, small team environment with a focus on building impactful, reliable AI solutions.
• Team activities include regular in-person meetings, brainstorming sessions, and social gatherings on Saturdays.

Salary

Not specified.

GrowthOpportunities

Not specified.

Benefits

Not specified.