Senior AI Engineer

Senior AI Engineer

Company: Techjays

Experience: 4–8 Years

Location: Coimbatore, Hybrid

Joining: Immediate or within 30 days preferred

About the Role

We are looking for a Senior AI Engineer with strong Python development skills and hands-on experience building and deploying AI-powered applications. The ideal candidate should have practical knowledge of LLMs, Retrieval-Augmented Generation (RAG), vector databases, and scalable backend systems.

You will work closely with engineering and product teams to design, develop, and deploy reliable AI solutions for real-world business problems.

Key Responsibilities

• Design, develop, and maintain scalable backend applications using Python and frameworks such as Django, Flask, or FastAPI.
• Build and integrate AI-powered applications using LLMs, RAG pipelines, and agentic AI workflows.
• Develop document processing, embedding generation, semantic search, and retrieval pipelines.
• Integrate LLM APIs and optimize prompts, response quality, latency, and cost.
• Work with vector databases and relational databases to build efficient data retrieval systems.
• Design and implement REST APIs, asynchronous processing, caching, and queuing mechanisms.
• Apply software engineering best practices, including design patterns, clean code, testing, and version control.
• Deploy and maintain applications on AWS or GCP using Docker and CI/CD pipelines.
• Monitor production systems, troubleshoot issues, and improve application performance and reliability.
• Collaborate with cross-functional teams to translate business requirements into practical AI solutions.
• Contribute to code reviews, technical documentation, and knowledge sharing within the engineering team.

Required Skills

• 4–8 years of experience in software development, with strong hands-on Python expertise.
• Strong understanding of data structures, algorithms, object-oriented programming, and design patterns.
• Experience building backend applications using Django, Flask, or FastAPI.
• Hands-on experience with LLM-based applications and API integrations.
• Practical experience implementing RAG pipelines, embeddings, and semantic search.
• Experience with vector databases such as Pinecone, Qdrant, Weaviate, or Chroma.
• Strong knowledge of SQL and relational databases such as PostgreSQL or MySQL.
• Experience with caching, message queues, asynchronous processing, and WebSockets.
• Familiarity with AWS or GCP, Docker, Git, and CI/CD pipelines.
• Understanding of API design, system architecture, application security, and performance optimization.
• Experience testing, debugging, and maintaining production-grade applications.

Preferred Skills

• Experience building agentic AI applications and multi-agent workflows.
• Familiarity with LangChain, LangGraph, LlamaIndex, or similar frameworks.
• Knowledge of Model Context Protocol (MCP) and tool-calling mechanisms.
• Experience with LLM evaluation, hallucination reduction, and output quality monitoring.
• Familiarity with fine-tuning, model selection, and inference optimization.
• Experience with LLMOps, AI observability, and production monitoring.
• Knowledge of Kubernetes and microservices architecture.

What We’re Looking For

• Strong problem-solving and analytical skills.
• Ability to take ownership of features from development through deployment.
• Practical understanding of how to build reliable AI applications beyond prototypes.
• Ability to make sound technical decisions and explain architectural trade-offs.
• Good communication and collaboration skills.
• Willingness to learn, experiment, and work on challenging AI engineering problems.

Skills

Python, Retrieval Augmented Generation (RAG), Model Context Protocol (MCP), Artificial Intelligence (AI), Anthropic Claude, Agentic AI