Agentic AI Engineer

This role centers on architecting and implementing intelligent AI agent systems built on large language models (LLMs) and current AI tooling. You’ll work with autonomous agents, orchestrate multi-step workflows, build backend services, and deploy AI applications on cloud infrastructure while maintaining high scalability, reliability, and performance. The position also calls for working closely with different teams to ship AI-driven enterprise solutions using container and cloud platforms.

Key Responsibilities

• Architect and implement agentic AI systems, self-directed agents, and multi-agent workflows
• Create and refine LLM-based apps that perform reasoning, planning, and task completion
• Use frameworks such as LangChain, LangGraph, AutoGen, CrewAI, and comparable libraries
• Craft APIs, utilities, and backend services that let AI agents act and automate work
• Set up memory layers, vector stores, and retrieval pipelines for AI solutions
• Establish evaluation and testing flows to raise AI dependability, precision, and speed
• Engineer scalable backend services with Python or http://Node.js
• Connect AI systems to enterprise software, microservices, cloud platforms, and data stores
• Put CI/CD pipelines in place and run containerized deployments via Docker and Kubernetes
• Enable AI workloads on cloud providers including AWS, Azure, or GCP
• Run PoC initiatives, compare models, and tune runtime performance
• Watch system metrics and enhance scalability, observability, and resilience
• Partner with engineering, product, and business groups to release AI-enabled products
• Draft technical docs, system diagrams, and deployment runbooks
• Investigate system faults and help with root-cause debugging
• Adopt best practices for building secure, scalable, and robust AI applications
• Track new developments in LLMs, AI agents, and cloud tooling
• Own AI engineering and deployment activities from start to finish

Required Skills

• Solid coding ability in Python
• Proven background creating AI/ML apps and backend services
• Practical experience with LLM integrations, prompt design, and reasoning chains
• Familiar with agent frameworks like LangChain, LangGraph, AutoGen, CrewAI, or equivalents
• Good grasp of AI/ML ideas, embeddings, RAG pipelines, and model fine-tuning
• Skilled at building REST APIs, microservices, and high-scale backend systems
• Comfortable with Docker, Kubernetes, and container-based deployments
• Knowledge of cloud platforms such as AWS, Azure, or GCP
• Exposure to CI/CD tools including GitHub Actions, GitLab, or Jenkins
• Understanding of vector databases like Pinecone, FAISS, Chroma, or Weaviate
• Strong troubleshooting, analytical thinking, and problem resolution skills
• Able to design trustworthy AI systems with safety checks and fallback paths
• Clear communicator with strong collaboration and team skills
• Thrives in agile, fast-moving engineering environments
• Sound knowledge of software architecture and cloud-native design

Preferred Skills

• Prior work on enterprise AI transformation initiatives
• Exposure to workflow orchestration and autonomous agent systems
• Familiar with observability stacks, monitoring, and logging tools
• Knowledge of large-scale distributed systems and cloud cost/performance tuning
• Understanding of AI safety, governance, and guardrail design
• Experience with current AI serving and inference platforms
• Exposure to sophisticated prompt strategies and multi-agent coordination
• Keen interest in new AI tech and intelligent automation

Education

• B.Tech / BCA / MCA / http://B.Sc. in Computer Science, IT, Artificial Intelligence, Data Science, Engineering, or Equivalent Qualification*

Technology: Python REST APIs LLM LangChain AI/ML RAG Pipelines

Job Type: Full Time

Job Location: Bengaluru

Work Mode: Onsite / Hybrid

Experience: 2 to 5 Years