Python AI EngineerRole Overview
Total Exp: 6+ yrs
Notice: Immediate only
If interested please apply here or share cv to [email protected]
Location: Bangalore (Hybrid)/Anywhere in India (Remote)
We are looking for a Python AI Engineer to design, develop, and deploy scalable, production-grade AI applications and services. The ideal candidate will have strong expertise in Python, FastAPI, Generative AI, LLMs, RAG, AI agents, cloud technologies, and microservices architecture.
The role involves building enterprise AI solutions, integrating LLMs and AI services, and developing secure, scalable backend systems.
Key ResponsibilitiesAI & Generative AI
- Build AI-powered applications including RAG systems, AI copilots, conversational AI, and intelligent agents.
- Integrate LLMs such as OpenAI, Azure OpenAI, Anthropic, Gemini, and Llama.
- Design RAG pipelines, prompt engineering, embeddings, semantic search, and LLM orchestration.
- Build AI workflows using LangChain, LangGraph, Semantic Kernel, CrewAI, or similar frameworks.
- Implement vector search using Pinecone, Weaviate, ChromaDB, FAISS, or equivalent technologies.
- Develop agentic AI solutions using tool/function calling and enterprise system integrations.
- Support AI evaluation, monitoring, deployment, and optimization.
Python & Backend Engineering
- Design and develop high-performance APIs and backend services using Python and FastAPI.
- Build scalable microservices and asynchronous applications.
- Develop integrations with third-party APIs and enterprise systems.
- Implement authentication, authorization, security, logging, and error handling.
- Optimize application performance, scalability, reliability, and maintainability.
- Apply strong software engineering practices including OOP, design patterns, clean architecture, and asynchronous programming.
Data & Cloud
- Work with PostgreSQL, MongoDB, and Redis for application and AI workloads.
- Build containerized applications using Docker and deploy using Kubernetes.
- Develop and deploy solutions on Azure, AWS, or GCP.
- Implement CI/CD pipelines, monitoring, logging, and production support.
Collaboration & Engineering
- Participate in technical design and architecture discussions.
- Conduct code reviews and contribute to engineering standards and best practices.
- Collaborate with AI, data, product, and engineering teams to translate business requirements into scalable AI solutions.
Required Skills
- Strong hands-on expertise in Python.
- Strong experience with FastAPI, REST APIs, microservices, and asynchronous programming.
- Hands-on experience building production-grade Generative AI/LLM applications.
- Strong understanding of RAG, vector databases, embeddings, prompt engineering, and LLM orchestration.
- Experience with LangChain, LangGraph, Semantic Kernel, CrewAI, or similar frameworks.
- Experience with one or more LLM platforms: OpenAI, Azure OpenAI, Anthropic, Gemini, or Llama.
- Experience with PostgreSQL and/or NoSQL databases.
- Hands-on experience with Docker, CI/CD, and at least one major cloud platform.
- Understanding of AI agents, tool calling, model evaluation, and AI observability.
Preferred Qualifications
- Experience building Agentic AI and enterprise AI solutions.
- Experience with Microsoft Copilot ecosystem / Semantic Kernel.
- Exposure to Databricks, Microsoft Fabric, or other enterprise data platforms.
- Experience with Neo4j or graph-based solutions.
- Understanding of MLOps/LLMOps, AI governance, security, and responsible AI.
- Experience working in enterprise or consulting environments.
Education
- Bachelor's or Master's degree in Computer Science, Engineering, Information Technology, or a related field.
- Relevant Cloud, AI, or Data Engineering certifications are a plus.