Fullstack Engineer

Legalease Solutions; Chennai District; Hybrid; INR 3,000,000 - 6,000,000; Full time

Job summary

Legalease Solutions in Chennai seeks a Product Lead for AI-Native Full Stack workflows, combining frontend, backend, and agent logic to ship production-grade legal automation.

You will own end-to-end development, wire up LLMs, RAG pipelines, and ensure guardrails with human-review steps, all in a fast-moving, small-team setting.

5+ years of experience in full-stack or product leadership is expected; location is Chennai with a focus on agentic legal workflows for law firms.

Job description

Designation: Product Lead Fullstack development AI-Native Full Stack Engineer Agentic Legal Workflows Location:- Chennai

Experience:- 5+ years

Why this role exists Law firms are entering the agentic AI era and small and mid-size firms are where we see the biggest opportunity. We build custom, secure agentic legal workflows around how each firm actually drafts, reviews, negotiates, researches, and manages work, instead of forcing every firm into the same generic tool. The goal is scale and efficiency: give a small or mid-size firm the leverage to take on more work without adding headcount at the same rate. This isn't a chatbot bolted onto practice management software. It's production software that ships fast, gets used by real attorneys at real firms, and gets judged on whether it actually helped a firm grow not on how good the demo looked. We are a small team. There is no separate "AI team" and "product team" you own both. If you've ever waited three sprints for someone else to wire up a model, this role doesn't have that problem. You'll go from "this firm drafts contracts this way" to a shipped, monitored, cost optimized agentic workflow, often in the same week.

What you’ll actually do

Ship end-to-end AI-powered workflows frontend, backend, agent logic, evals as one person, not as a relay race across three teams.

Build multi-step agentic workflows that retrieve documents, use tools, and complete drafting, review, and research tasks a paralegal or associate would otherwise do by hand.

Wire up LLMs, RAG pipelines, and document-processing chains against real legal source material not toy datasets and adapt them to each firm's practice area and working style.

Put guardrails around everything: evals, monitoring, fallback paths, and a human-review step for anything that touches legal risk. No silent failures in front of a client's attorney.

Own token economics like a founder owns burn routing, caching, batching, and picking the right model for the right step, because solo and small-firm pricing only works if delivery cost stays low.

Use coding agents and AI-assisted dev tools as your default way of writing software we expect you to move faster because of AI, not despite the extra tooling .

Sit close to attorneys and legal engineers so the workflows you build reflect how legal work actually happens at a small firm, not how engineers assume it happens.

What gets you shortlisted

57 years shipping production software full‑stack — you …

Comfortable ... etc ...