Job Description

We are looking for an experienced AI Engineer with strong expertise in backend development, Large Language Models (LLMs), AI agent architecture, and cloud infrastructure. The ideal candidate will be responsible for designing, developing, deploying, and optimizing production-ready AI systems, including multi-agent architectures, retrieval pipelines, and scalable backend services.

This role requires hands-on experience in AI engineering, backend development, infrastructure management, and production monitoring, with a strong focus on performance, reliability, cost optimization, and scalability.

Key Responsibilities1. Multi-Agent System Architecture

- Design and scale multi-agent orchestration systems with multiple specialized AI agents.
- Implement parallel execution, conditional routing, and shared-state management.
- Develop domain-specific agents with customized retrieval pipelines, prompts, tools, and fallback mechanisms.
- Build graph-based routing logic to support dynamic task execution.

2. LLM Integration and Optimization

- Integrate and manage multiple LLM models and providers.
- Select appropriate models based on cost, latency, and accuracy.
- Develop and optimize prompt systems for improved response quality.
- Optimize token usage, response time, and overall AI performance.

3. Retrieval and Knowledge Systems

- Build hybrid search pipelines using vector search, keyword search, and metadata filtering.
- Optimize document chunking, indexing, embeddings, and reranking strategies.
- Improve context retrieval quality for LLM-based applications.

4. Backend Development and Infrastructure

- Develop scalable backend services for AI applications and pipelines.
- Implement streaming responses and asynchronous processing.
- Deploy and manage AI services using cloud infrastructure.
- Maintain CI/CD pipelines and production environments.

5. Monitoring and Reliability

- Build monitoring systems to track latency, errors, and model performance.
- Identify hallucinations,



failure scenarios, and edge cases.
- Implement fallback mechanisms and reliability improvements.
- Troubleshoot and resolve production issues.

6. Cost and Performance Optimization

- Optimize AI inference costs across models and workflows.
- Balance cost, response quality, and latency.
- Continuously improve system efficiency, scalability, and reliability.

Required Skills and Qualifications

- 3–5 years of relevant experience in AI engineering, backend development, or related technical roles.
- Strong backend development experience, preferably using Python.
- Hands-on experience building and deploying LLM-based applications in production.
- Experience with vector databases, embeddings, and retrieval-augmented generation (RAG) systems.
- Understanding of distributed systems and asynchronous processing.
- Familiarity with cloud platforms such as AWS, Google Cloud Platform (GCP), or Microsoft Azure.
- Experience developing scalable, reliable, and production-ready applications.
- Strong debugging, analytical, and problem-solving skills.

Preferred Skills

- Experience with multi-agent frameworks and orchestration systems.
- Knowledge of prompt engineering and LLM optimization at scale.
- Experience developing real-time AI applications.
- Familiarity with monitoring, logging, and observability tools.
- Strong ownership and ability to work across AI, backend, and infrastructure.
- Practical, delivery-focused approach to solving complex technical challenges.

What We Offer

- Opportunity to work on advanced AI systems and production-scale applications.
- Exposure to multi-agent architectures, LLM integration, and modern cloud infrastructure.
- Opportunities to solve challenging engineering problems and contribute to creative technology solutions.
- Collaborative and growth-oriented work environment.

Interested candidates with hands-on experience in production AI systems, LLMs, Python backend development, and RAG pipelines are encouraged to apply.

Pay: ₹300,000.00 - ₹500,000.00 per year

Work Location: In person

📌 AI Engineer – Full Stack AI, Backend & Infrastructure (Kharadi)
🏢 Cybic Technologies
📍 Kharadi