AI Engineer – LLM & Agentic Systems

Navaris Digital; Pune District; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

Navaris Digital is seeking an AI Engineer to design, build, and deploy production-ready LLM applications and RAG pipelines. You will drive end-to-end development from indexing to agent orchestration, ensuring scalable, accurate AI systems with well-documented architecture.

You will work on embedding-based retrieval, semantic search, and tool integrations, building robust RESTful services and microservices with strong system design and debugging skills.

Qualifications

• Experience building LLM-powered applications and RAG systems.

Responsibilities

• Design end-to-end RAG pipelines (document processing, vector indexing, semantic retrieval).
• Integrate LLMs to generate context-grounded responses.
• Develop and orchestrate multi-agent AI systems with structured handoffs.
• Implement tool integrations for FAQs, external workflows.
• Manage per-user session context and state across agents.
• Write clean, modular, well-documented code.
• Test, debug, and optimise system performance and retrieval accuracy.
• Document architecture decisions and trade-offs.
• Collaborate with stakeholders to refine requirements.

Skills

LLM-powered

RAG systems

semantic search

Python

RESTful APIs

microservices

context/session management

debugging/optimisation

clear documentation

Tools

LangChain

LangGraph

FAISS

Chroma

Pinecone

Azure Cognitive Search

Job description

About The Role

We are seeking an AI Engineer to design and build production-ready LLM applications, including Retrieval-Augmented Generation (RAG) pipelines and multi-agent AI systems. The role focuses on strong system design, clean architecture, and practical implementation of intelligent, tool-integrated solutions. You will be responsible for end-to-end development — from document indexing and semantic retrieval to agent orchestration and context management — ensuring scalable, accurate, and well-documented AI systems.

Responsibilities

• Design and implement end-to-end RAG pipelines including document processing, vector indexing, and semantic retrieval
• Integrate LLMs to generate accurate, context-grounded responses
• Develop and orchestrate multi-agent AI systems with structured handoffs
• Implement tool integrations for FAQs, seat updates, and external workflows
• Manage per-user session context and state across agent interactions
• Write clean, modular, and well-documented code
• Test, debug, and optimise system performance and retrieval accuracy
• Document architecture decisions, assumptions, and trade-offs
• Collaborate with stakeholders to refine requirements and improve solutions

Requirements

• Experience building LLM-powered applications and RAG systems
• Strong understanding of embeddings, vector databases, and semantic search
• Hands‑on experience with frameworks such as LangChain, LangGraph, or similar
• Proficiency in Python and building RESTful APIs
• Experience integrating external tools and APIs within AI workflows
• Solid understanding of system design, microservices, and scalable architectures
• Ability to manage session state and context in conversational systems
• Strong debugging, problem‑solving, and optimisation skills
• Clear communication skills with the ability to explain technical decisions and trade-offs

Nice to Have

• Experience with agent orchestration frameworks and multi-agent architectures
• Hands‑on experience with FAISS, Chroma, Pinecone, or Azure Cognitive Search
• Experience deploying AI systems using Docker and Kubernetes
• Familiarity with cloud platforms such as AWS, Azure, or GCP
• Experience with evaluation frameworks for LLM performance and retrieval quality
• Knowledge of prompt engineering and guardrail implementation techniques
• Experience building production‑grade chatbots or conversational AI systems
• Understanding of CI/CD pipelines and DevOps best practices

What We Offer

• Opportunity to work on cutting-edge Generative AI and agentic systems
• High ownership and autonomy in technical decision-making
• Exposure to real-world, production-grade AI implementations
• Collaborative and innovation-driven work environment
• Flexible work arrangements
• Competitive compensation and growth opportunities
• Opportunity to shape AI architecture and best practices from the ground up
• Continuous learning and skill development in emerging AI technologies