3–6 yrsGurugramOn-siteDirect career pageEst. 18–30 LPA
Posted on 22 Sept
Reach people at Lawyered (Sproutech Solutions Private Limited)
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Lawyered (Sproutech Solutions Private Limited) you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Architect and deploy autonomous and semi-autonomous legal AI agents managing end-to-end workflows such as intake, research, drafting, filing, and follow-ups.
- Design systems ensuring agent reliability, auditability, safety, and compliance in a regulated legal domain, including human-in-the-loop controls and escalation protocols.
- Own agent evaluation metrics, observability with full audit trails, cost and latency optimizations, and compliance with data protection laws like DPDP Act.
Minimum Requirements
- 3+ years software/ML engineering experience with at least 1 year building large language model (LLM) agents in production environments.
- Strong proficiency in Python, backend systems (APIs, Postgres, queues, async), and cloud deployment (AWS/GCP).
- Experience with agent frameworks (LangGraph, CrewAI, AutoGen, Claude/OpenAI Agents SDK), tool use and function calling including MCP, and multi-step agent evaluation and debugging.
- Work Experience Required: 3+ years with 1+ year LLM agent production experience; Location: Gurgaon (Hybrid).
Ideal Candidate Profile
- Expertise in building complex multi-agent workflows within regulated domains, focused on operational reliability and legal compliance.
- Experienced in implementing advanced AI agent functionalities such as task decomposition, reflection loops, agent memory management, and human-in-the-loop approval mechanisms.
- Familiar with RAG techniques (embeddings, vector DBs, hybrid search), browser automation, durable workflow engines, and India-specific legal and technical ecosystems.