AI Engineer — Generative AI & Agentic AI

Code1 Tech Systems; India; On-site; INR 3,000,000 - 6,000,000; Full time

Job summary

Code1 Tech Systems is seeking engineers to build next-generation AI systems powered by Generative AI and agentic architectures. You will design and deliver production-grade AI solutions, including conversational systems and document intelligence, with a focus on scalable backends and robust prompts.

The role demands strong programming fundamentals and hands-on experience with LLMs, RAG, and multi-agent frameworks to drive real-world, production-ready AI applications across teams.

Qualifications

• 6+ years experience building AI-driven systems.
• Proven ability to design production-grade AI solutions.
• Hands-on experience with LLMs in real-world apps.

Responsibilities

• Design and implement agentic AI systems with multi-agent workflows.
• Build Generative AI apps using LLMs for conversational AI and automation.
• Develop RAG pipelines using vector databases and semantic search.
• Integrate multiple LLMs and models for performance and cost balance.
• Design scalable backend APIs to support AI apps.
• Implement prompt engineering and guardrails for reliability.
• Monitor AI system performance and optimize latency and cost.

Skills

Python

LLMs

Generative AI

Agentic AI

API design

Vector databases

Backend development

Tools

LangChain

LangGraph

CrewAI

Docker/Kubernetes

Job description

We Are

At Code1 Tech, we drive innovations that shape the future of enterprise technology. Our expertise spans Data Engineering, AI/ML, Cloud Solutions, and Full-Stack Development. We empower businesses with cutting edge technology solutions, enabling digital transformation at scale. Join us to build impactful products with a passionate team of engineers and innovators.

About The Role

We are looking for engineers to build next-generation AI systems powered by Generative AI and Agentic AI architectures. This role focuses on developing intelligent systems that can reason, act, and automate complex workflows using large language models and multi-agent frameworks.

You will work on designing and delivering production-grade AI solutions, including conversational systems, document intelligence, decision automation, and AI-driven applications. The role requires strong engineering fundamentals along with hands-on experience in building, integrating, and scaling AI systems beyond prototypes.

Experience: 6+ Years

Key Responsibilities:

• Design and implement agentic AI systems, including multi-agent workflows, orchestration logic, and tool-integrated agents
• Build Generative AI applications using LLMs for use cases such as conversational AI, content generation, and intelligent automation
• Develop Retrieval-Augmented Generation (RAG) pipelines using vector databases and semantic search techniques
• Integrate and work with multiple LLMs and AI models, selecting and optimizing them based on performance, cost, and use case requirements
• Design and develop scalable backend systems and APIs to support AI applications
• Implement prompt engineering strategies, structured outputs, and guardrails to improve model reliability
• Evaluate, monitor, and optimise AI system performance, including accuracy, latency, and cost efficiency
• Collaborate with cross-functional teams to translate business requirements into AI-driven solutions
• Stay updated with advancements in Gen AI, agentic frameworks, and emerging AI tooling
• Contribute to system documentation, architecture discussions, and knowledge sharing across teams

Core Skills:

• Strong programming skills in Python (and familiarity with backend frameworks)
• Hands-on experience with Generative AI and LLMs in real-world applications
• Experience with RAG architectures, embeddings, and document processing pipelines
• Familiarity with agentic frameworks (such as LangChain, LangGraph, CrewAI, or similar)
• Understanding of API design, system architecture, and scalable backend development
• Experience with vector databases (e.g., Qdrant, Weaviate, FAISS, or similar)
• Solid understanding of prompt engineering, model behaviour, and output control techniques

Good To Have:

• Experience with multi-agent systems and workflow orchestration
• Exposure to knowledge graphs or hybrid retrieval systems
• Familiarity with cloud platforms and containerisation (Docker, Kubernetes)
• Experience in evaluation frameworks, monitoring tools, and model optimisation techniques
• Understanding of voice-based systems (STT/TTS) or multimodal AI applications
• Strong problem-solving ability with a focus on building scalable, production-ready systems
• Ability to work in fast-paced and ambiguous environments
• Ownership mindset with attention to quality, performance, and reliability
• Clear communication and ability to collaborate across teams

Ready to make an impact?