Senior AI Engineer

# Job Description: AI Engineer

## 1. Job Overview

**Job Title:** AI Engineer **Department:** Engineering / Artificial Intelligence **Experience:** 5–6 Years **Employment Type:** Full-Time **Work Mode:** Remote **Salary Range:** ₹18–22 LPA **Open Positions:** 2 **Joining:** Immediate Joiners / Candidates with Short Notice Period Preferred **Job Location:** Remote – India

## 2. About the Role

We are looking for a skilled and hands-on AI Engineer to design, develop, integrate, and deploy AI-powered applications and intelligent systems. The ideal candidate should have strong expertise in Python programming, Machine Learning, Large Language Models (LLMs), Generative AI, and modern AI application development frameworks.

The candidate will be responsible for building scalable AI solutions, developing intelligent conversational systems, implementing Retrieval-Augmented Generation (RAG) pipelines, integrating third-party AI models and APIs, and optimizing AI applications for performance, accuracy, reliability, and cost.

The ideal candidate should have practical experience taking AI solutions from proof of concept to production, along with a strong understanding of backend development, data processing, model evaluation, and deployment practices.

## 3. Key Responsibilities

### A. AI Application Development

• Design, develop, and deploy AI-powered applications to solve real-world business problems.
• Build intelligent systems using Machine Learning, Deep Learning, Generative AI, and Large Language Models.
• Translate business requirements into technical AI solutions and production-ready applications.
• Develop reusable, modular, scalable, and maintainable AI components.
• Evaluate emerging AI technologies and recommend appropriate solutions based on business requirements.

### B. Generative AI and LLM Engineering

• Develop and integrate applications using LLMs from providers such as OpenAI, Anthropic, Google, or open-source model ecosystems.
• Implement prompt engineering techniques, structured outputs, function calling, and tool use.
• Build conversational AI systems capable of understanding user intent, maintaining context, and generating relevant responses.
• Implement multi-step AI workflows and agentic applications where appropriate.
• Optimize model selection, response quality, latency, token consumption, and inference costs.
• Apply techniques such as prompt templates, output validation, context management, and fallback mechanisms.

### C. Retrieval-Augmented Generation (RAG)

• Design and implement end-to-end RAG pipelines for document-based and enterprise knowledge applications.
• Develop document ingestion, parsing, chunking, embedding generation, indexing, and retrieval workflows.
• Integrate vector databases and search technologies to retrieve relevant information.
• Implement semantic search, metadata filtering, hybrid search, and reranking where appropriate.
• Improve answer relevance, contextual accuracy, and grounding in retrieved information.
• Implement source attribution and citation mechanisms to reduce unsupported AI-generated responses.
• Evaluate and optimize retrieval quality and end-to-end RAG performance.

### D. Machine Learning and Model Development

• Develop, train, evaluate, and optimize Machine Learning models based on business needs.
• Apply supervised and unsupervised learning techniques to suitable use cases.
• Perform data preprocessing, feature engineering, model selection, and hyperparameter tuning.
• Work with relevant Deep Learning frameworks such as PyTorch or TensorFlow.
• Evaluate models using appropriate metrics and validate their performance against business objectives.
• Determine when to use existing foundation models, fine-tuning, traditional ML, or custom model development.

### E. AI Agents and Workflow Automation

• Develop AI agents that can use tools, APIs, and external systems to complete defined tasks.
• Build multi-step workflows with appropriate state management, validation, and error handling.
• Integrate agent frameworks such as LangChain, LangGraph, or equivalent technologies when suitable.
• Implement human-in-the-loop approval mechanisms for sensitive or consequential operations.
• Prevent uncontrolled tool execution and handle failed tool calls, invalid outputs, and unexpected user inputs.
• Evaluate agent reliability and ensure workflows remain predictable and observable.

### F. Backend Development and API Integration

• Develop AI service backends using Python frameworks such as FastAPI, Flask, or Django.
• Build REST APIs and integrate AI capabilities with frontend applications and existing business systems.
• Implement authentication, authorization, input validation, error handling, and logging.
• Integrate external APIs, databases, cloud services, and enterprise applications.
• Work with SQL and NoSQL databases to manage application and AI-related data.
• Ensure APIs are scalable, secure, reliable, and production-ready.

### G. Vector Databases and Data Engineering

• Work with vector databases such as Pinecone, Qdrant, Weaviate, Chroma, or FAISS.
• Develop data ingestion and transformation pipelines for structured and unstructured data.
• Generate and manage embeddings for semantic retrieval and similarity search.
• Work with PostgreSQL, MySQL, MongoDB, or equivalent databases as required.
• Optimize retrieval speed, indexing strategies, metadata management, and data quality.
• Implement data validation and synchronization mechanisms for AI applications.

### H. Model Evaluation, Testing, and Optimization

• Design evaluation frameworks to measure AI response quality, factual accuracy, relevance, and consistency.
• Create test datasets and test cases for LLM-powered applications.
• Perform regression testing when prompts, models, datasets, or retrieval configurations change.
• Evaluate hallucinations, retrieval failures, prompt injection risks, and inappropriate outputs.
• Monitor production performance, latency, errors, and AI service availability.
• Use automated evaluation and observability tools where appropriate.
• Continuously improve AI system quality through experimentation and feedback.

### I. Deployment, Cloud, and MLOps

• Deploy AI applications to production environments using Docker and cloud infrastructure.
• Work with AWS, Microsoft Azure, Google Cloud, or equivalent platforms.
• Implement CI/CD pipelines and automated testing for reliable releases.
• Use Git and standard software engineering practices for version control and collaboration.
• Monitor application health, model performance, resource utilization, and inference costs.
• Optimize deployments for scalability, availability, and operational efficiency.
• Support model versioning, configuration management, and reproducible deployments.

### J. Security and Responsible AI

• Implement appropriate safeguards for sensitive information and confidential business data.
• Apply secure API key management, access controls, and data protection practices.
• Understand prompt injection, data leakage, unsafe tool execution, and other LLM application risks.
• Implement input/output validation, rate limiting, and appropriate content safeguards.
• Follow responsible AI practices and applicable privacy and security requirements.
• Ensure AI outputs are appropriately validated before being used in critical workflows.

### K. Collaboration and Documentation

• Collaborate with product managers, software engineers, data scientists, and other stakeholders.
• Participate in technical discussions, architecture reviews, code reviews, and sprint planning.
• Document AI architecture, APIs, workflows, model configurations, and deployment procedures.
• Explain technical trade-offs, implementation decisions, and model limitations clearly.
• Take ownership of assigned features from design and development through testing and production deployment.

## 4. Required Technical Skills

### Programming and Backend

• Strong proficiency in Python.
• Good understanding of object-oriented programming, data structures, algorithms, and software design principles.
• Hands-on experience developing backend services using FastAPI, Flask, or Django.
• Experience building and consuming REST APIs.
• Strong debugging, testing, and problem-solving skills.

### Generative AI and LLMs

• Practical experience building applications using Large Language Models.
• Strong understanding of prompt engineering, context windows, tokenization, and structured outputs.
• Experience integrating commercial or open-source LLMs.
• Knowledge of embeddings, semantic similarity, and vector search.
• Hands-on experience implementing RAG-based applications.
• Understanding of hallucination mitigation, model limitations, and response evaluation.

### AI Frameworks and Libraries

Experience with relevant technologies such as

• LangChain and/or LangGraph.
• Hugging Face Transformers.
• PyTorch and/or TensorFlow.
• Scikit-learn.
• LlamaIndex or equivalent RAG frameworks.
• NumPy and Pandas.

### Databases and Search

• Experience with SQL databases such as PostgreSQL or MySQL.
• Familiarity with vector databases such as Pinecone, Qdrant, Weaviate, Chroma, or FAISS.
• Understanding of data modeling, indexing, and query optimization.
• Knowledge of document processing and unstructured data retrieval.

### Cloud and Deployment

• Hands-on experience deploying applications to a cloud environment.
• Working knowledge of Docker and containerization.
• Familiarity with Git, CI/CD, logging, and monitoring.
• Understanding of production application architecture, scalability, and performance optimization.

## 5. Preferred Skills

• Experience building production-grade AI assistants, chatbots, or enterprise AI applications.
• Experience implementing agentic workflows and tool-calling systems.
• Familiarity with model fine-tuning, LoRA/PEFT, or other parameter-efficient training techniques.
• Experience with reranking, hybrid search, and advanced RAG optimization.
• Knowledge of model serving and inference optimization.
• Experience with asynchronous Python, background jobs, caching, and rate limiting.
• Familiarity with LLM evaluation frameworks such as Ragas, DeepEval, or equivalent tools.
• Understanding of AI security, guardrails, observability, and responsible AI practices.
• Experience with Redis, message queues, or event-driven architectures.
• Experience working in Agile development environments.

## 6. Minimum Qualifications

• Bachelor's degree in Computer Science, Information Technology, Artificial Intelligence, Data Science, or a related field, or equivalent practical experience.
• 3–6 years of relevant software engineering, AI engineering, or Machine Learning experience.
• Demonstrable hands-on experience developing AI/ML applications.
• Strong Python development skills and sound software engineering fundamentals.
• Experience integrating AI models into usable applications or backend services.
• Ability to independently troubleshoot technical issues and deliver working solutions.

## 7. What We Are Looking For

The ideal candidate should

• Be a hands-on engineer who can write production-quality code rather than only experiment with AI tools.
• Have a strong understanding of the practical application of LLMs and Machine Learning.
• Be capable of independently designing, implementing, testing, and deploying AI features.
• Understand the trade-offs between model accuracy, cost, latency, and scalability.
• Be comfortable working in a fast-paced environment with evolving technical requirements.
• Demonstrate ownership, curiosity, analytical thinking, and a willingness to learn new technologies.

## 8. Interview Evaluation Areas

Candidates may be evaluated on the following

1. Python programming and problem-solving.
2. AI/ML fundamentals and practical implementation.
3. LLM integration, prompt engineering, and structured outputs.
4. RAG architecture, embeddings, and vector search.
5. Backend API development and database integration.
6. AI application testing, evaluation, and production deployment.
7. System design, debugging, and real-world project experience.

## 9. Compensation and Benefits

• **Salary:** ₹18–22 LPA, depending on experience and technical expertise.
• **Work Mode:** Fully Remote.
• **Employment:** Full-Time.
• **Openings:** 2.
• **Joining Preference:** Immediate joiners or candidates with a short notice period.