Artificial Intelligence Engineer

Insaito Software; India; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Insaito Software is seeking an AI Engineer to design, build, and deploy intelligent agent systems powering complex workflows. You will work across problem definition, model selection, deployment, and continuous optimization in a fast-paced environment.

The role emphasizes strong ML/LLM depth, LangChain/LangGraph experience, and scalable AI infrastructure across AWS/GCP/Azure. You will influence architecture and production reliability while collaborating with product and sales teams.

Qualifications

• 1–3 years of experience in AI/ML engineering, building and deploying production-grade ML or LLM-based systems.
• Strong hands-on experience with LLMs, Agentic AI systems, and multi-agent orchestration.
• Proficiency in LangChain, LangGraph, or similar ecosystems.
• Experience designing and optimizing RAG pipelines and document intelligence systems.

Responsibilities

• AI Systems: design, develop and optimize agentic AI systems and multi-agent architectures.
• Retrieval, Model Serving & AI Infrastructure: build RAG pipelines, vector search and deploy open models.
• Backend Engineering, APIs & Production Systems: develop Python-based services and REST APIs.
• Scalability & Technical Leadership: CI/CD, versioning, monitoring and cross-functional collaboration.

Skills

LLMs

Agentic AI

Multi-agent orchestration

LangChain

LangGraph

RAG pipelines

Python

Tools

FAISS

Pinecone

vLLM

TGI

LLaMA

Qwen

Job description

What we’re looking for

We are seeking a highly skilled AI Engineer to design, build, and deploy intelligent agent systems that power these workflows. This role involves working across the full lifecycle of AI product development - from problem definition and model selection to system architecture, deployment, and continuous optimization.

The AI Engineer will collaborate closely with product, sales, and leadership teams to translate real-world business problems into scalable AI solutions. The role requires strong technical depth in machine learning, LLMs, and system design, along with the ability to evaluate performance, ensure reliability, and iterate rapidly based on user feedback.

This is a high-impact role for someone who can combine engineering rigor with practical problem-solving to build production-grade AI systems and contribute to Automatans core product and long-term technology vision.

Responsibilities

1. AI Systems, Agentic Workflows & LLM Applications

• Design, develop, and optimize advanced Agentic AI systems and multi-agent architectures for complex business workflows.
• Manage scalable AI infrastructure across cloud platforms such as AWS, GCP, and Azure.
• Build intelligent agent workflows using frameworks such as LangChain and LangGraph, enabling reasoning, task execution, tool usage, and cross-agent coordination.
• Develop and enhance LLM-powered applications for use cases including document analysis, summarization, classification, workflow automation, hiring, sales, and operations.
• Apply advanced prompt engineering, evaluation frameworks, benchmarks, and feedback loops to improve output quality, consistency, and reliability.
• Research, evaluate, and implement state-of-the-art open-source models such as LLaMA, Qwen, and emerging foundation model architectures.
• Deploy, monitor, maintain, and continuously improve AI/ML systems in production environments.

2. Retrieval, Model Serving & AI Infrastructure

• Design, build, and optimize Retrieval-Augmented Generation (RAG) systems for high-accuracy, context-aware AI experiences.
• Manage end-to-end retrieval pipelines including data ingestion, chunking, embedding generation, vector storage, similarity search, and query optimization.
• Work with vector databases such as FAISS, Pinecone, and related retrieval technologies to improve relevance, latency, and scalability.
• Integrate LLM APIs, external tools, and enterprise systems into AI applications to enable dynamic, tool-augmented workflows.
• Deploy, serve, and optimize open-source models using frameworks such as vLLM and Text Generation Inference (TGI), ensuring performance, reliability, and cost efficiency.

3. Backend Engineering, APIs & Production Systems

• Develop scalable Python-based backend services, microservices, and RESTful APIs for AI applications and model orchestration.
• Build robust systems for model serving, workflow execution, and seamless integration with external applications.
• Ensure modular, reusable, maintainable, and production-grade code architecture across AI platforms.
• Optimize application performance, fault tolerance, observability, logging, and operational reliability.

4. Scalability & Technical Leadership

• Implement best practices for CI/CD, model versioning, experimentation, monitoring, and performance tracking.
• Collaborate closely with product, sales, leadership, and customer-facing teams to translate business requirements into AI solutions.
• Provide technical leadership on architecture decisions, feasibility assessments, trade-offs, solution design, and long-term AI strategy.
• Establish engineering best practices, technical standards, and scalable development processes across AI initiatives.

Skills and Experience

• 1 to 3 years of experience in AI/ML engineering, building and deploying production-grade machine learning or LLM-based systems.
• Strong hands-on experience with LLMs, Agentic AI systems, and multi-agent orchestration.
• Proficiency in building applications using frameworks such as LangChain, LangGraph, or similar ecosystems.
• Experience designing and optimizing RAG (Retrieval-Augmented Generation) pipelines and document intelligence systems.
• Solid understanding of vector databases such as FAISS, Pinecone, or similar technologies.
• Strong programming skills in Python, with experience in building scalable backend systems and APIs.
• Experience working with model inference frameworks such as vLLM, TGI, or equivalent.
• Familiarity with deploying and managing open-source LLMs such as LLaMA, Qwen, or similar models.
• Experience with cloud platforms (AWS, GCP, or Azure) and deploying scalable AI systems in production.
• Strong understanding of system design, performance optimization, latency management, and cost efficiency.
• Ability to evaluate model performance, debug issues, and improve reliability in real-world applications.
• Comfortable working in a fast-paced, early-stage environment with high ownership and ambiguity.
• Strong problem-solving, communication, and cross-functional collaboration skills.

Preferred Qualifications

• Experience building Agentic AI products or AI copilots in production environments.
• Familiarity with multi-agent coordination, tool usage frameworks, and autonomous workflows.
• Hands-on experience with MLOps practices, including CI/CD pipelines, model versioning, and monitoring.
• Experience working with large-scale unstructured data, document processing, and knowledge systems.
• Exposure to fine-tuning, embeddings optimization, or custom model training workflows.
• Prior experience in a startup or high-growth product environment.
• Ability to contribute to technical architecture decisions and long-term AI strategy.
• Experience collaborating closely with product, sales, or customer-facing teams to ship AI solutions.
• Understanding of enterprise use cases across operations, compliance, hiring, or business workflows.