Posted on: 22/12/2025
Description :
Experience : 5+ Years (Backend) | 1-2+ Years (AI/LLM)
Location : Bangalore
Work Mode : Hybrid
Role Overview :
We are seeking a highly skilled AI Engineer with strong hands-on experience in building, deploying, and scaling LLM-powered applications. The ideal candidate will have deep expertise in Python-based backend development and proven experience working with agent frameworks, API services, and AI orchestration pipelines.
This role involves designing intelligent systems that integrate large language models into real-world production workflows.
Key Responsibilities :
AI & LLM Engineering :
- Design, develop, and integrate LLM-powered systems using modern frameworks.
- Build intelligent agent workflows for reasoning, tool usage, memory, and orchestration.
- Implement prompt engineering, model evaluation, and inference pipelines.
- Optimize LLM workflows for performance, reliability, and cost.
Backend Development :
- Develop robust, scalable backend services using Python and FastAPI.
- Build secure and high-performance APIs and gateways.
- Handle async execution, background tasks, and API orchestration.
- Integrate AI services with existing data pipelines and systems.
Architecture & Delivery :
- Design production-grade AI architectures and microservices.
- Collaborate with product, frontend, and DevOps teams to deliver end-to-end solutions.
- Ensure reliability, monitoring, logging, and observability of AI services.
- Participate in code reviews, design discussions, and technical decision-making.
Required Skills & Experience :
Core Requirements :
- 5+ years of backend development experience.
- 1- 2+ years of hands-on experience working with AI/LLM systems.
- Strong proficiency in Python for backend and AI workflows.
- Hands-on experience with FastAPI (API design, async execution, services).
- Experience with LangChain and LangGraph (agents, tools, memory, orchestration).
- Strong understanding of LLM integration (prompting, orchestration, evaluation).
AI & Data Skills :
- Experience in building and deploying AI pipelines in production.
- Understanding of model evaluation, prompt optimization, and guardrails.
- Familiarity with vector databases and retrieval-based systems (nice to have).
Interview Process :
- HackerRank Assessment
- Technical Round(s) (1-2 rounds)
- HR Round
Why Join Us :
- Work on cutting-edge AI and LLM-powered products
- Opportunity to design real-world agent-based AI systems
- Competitive compensation and growth opportunities
- Collaborative, fast-paced engineering environment
Did you find something suspicious?