AIML Engineer

Lorven Technologies Inc.; Tamil Nadu; On-site; INR 1,800,000 - 2,800,000; Full time

Job summary

Lorven Technologies Inc. in India seeks an AI/ML Engineer to design, build, and deploy agentic AI systems, moving beyond prompt engineering to multi-agent workflows, memory and state management, and robust guardrails.

You will use LangChain and LangGraph to create autonomous agents, integrate with databases and APIs, and deploy on cloud platforms with MLOps practices.

Qualifications

• Strong knowledge of AI/ML concepts with experience building agent-based systems.
• Proficiency in Python and modern ML libraries.
• Experience with LangChain, LangGraph, and RAG workflows.
• Ability to design scalable, production-ready LLM applications.

Responsibilities

• Design and implement autonomous AI agents and multi-agent workflows.
• Develop production-grade LLM applications and tools.
• Optimize retrieval-augmented generation pipelines and memory systems.
• Ensure evaluation and safety guardrails for agent behavior.
• Integrate agents with internal databases and external APIs.
• Deploy and monitor environments in cloud platforms using MLOps.

Skills

Python

LangChain

LangGraph

Prompt engineering

LLM architectures

Vector databases

REST APIs

DevOps

Tools

Git

Docker

FastAPI

Job description

We are seeking a talented AI/ML Engineer to design, build, and deploy next-generation Agentic AI systems. In this role, you will move beyond simple prompt engineering to build autonomous, multi-agent workflows, stateful applications, and cognitive architectures. You will leverage LangChain and LangGraph to develop resilient AI agents capable of reasoning, planning, and executing complex tasks to solve real-world business problems.

Key Responsibilities

• Agentic Architecture: Design and implement autonomous AI agents and multi-agent systems using LangGraph for stateful, cyclic orchestration.
• LLM Application Development: Build production-grade LLM applications, chains, and custom tools using LangChain.
• Advanced RAG: Develop and optimize Advanced Retrieval-Augmented Generation (RAG) pipelines using vector databases and hybrid search techniques.
• Memory & State Management: Implement complex memory systems (short-term, long-term, and conversational) to maintain context in multi-turn agent interactions.
• Evaluation & Guardrails: Establish rigorous evaluation frameworks (using tools like TruLens, Ragas, or LangSmith) and safety guardrails for agent behavior.
• Model Fine-Tuning & Selection: Evaluate, select, and fine-tune open-source and proprietary LLMs (e.g., OpenAI, Anthropic, Llama) for specific agent tasks.
• API Integration: Connect AI agents securely to internal databases, external APIs, and enterprise software systems.
• Production Deployment: Deploy, monitor, and scale agentic workflows in cloud environments (AWS/GCP/Azure) using LLMOps best practices.

Required Technical Skills

• Core Languages: Mastery of Python and standard ML libraries (NumPy, Pandas, Scikit-learn).
• Frameworks: Deep hands‑on experience with LangChain and LangGraph (essential).
• Generative AI: Strong understanding of LLM architectures, prompt engineering, and agent patterns (ReAct, Plan-and-Solve, Reflection).
• Vector Databases: Experience with vector stores like Pinecone, Chroma, Milvus, or Qdrant.
• Software Engineering: Proficient with Git, Docker, and building RESTful APIs (FastAPI/Flask).
• Cloud & DevOps: Familiarity with cloud platforms and basic CI/CD pipelines.