Heavy focus on agentic AI and generative tooling; uses agent frameworks and LLM orchestration for building autonomous workflows.
About the Role
Senior Agentic AI Developer to design, build, and deploy multi-agent and agentic generative AI solutions, focusing on autonomous workflows, RAG/IR architectures, and production LLM orchestration. Role is full-time, hybrid in Bengaluru, and centers on integrating agent frameworks, vector DBs, cloud LLM platforms, and MLOps practices to deliver scalable business outcomes.
Job Description
Role
Senior Agentic AI Developer responsible for designing, developing, and deploying multi-agent systems and agentic applications that enable autonomous decision-making and workflow automation. The role focuses on generative AI, LLM orchestration, RAG/Information Retrieval architectures, and production-grade deployment across cloud and on-prem infrastructure. This is a full-time, hybrid role based in Bengaluru.
Key Responsibilities
- Design, develop, and deploy multi-agent systems and agentic applications using frameworks like AutoGen, LangGraph, CrewAI, or similar.
- Build intelligent workflow orchestration systems to enable autonomous task execution and decision-making.
- Implement Agent-to-Agent (A2A) communication protocols and Model Context Protocol (MCP) to enable agent collaboration.
- Integrate and implement OpenAPI-based automation for enterprise system interactions.
- Design self-healing, adaptive workflows that optimize business processes autonomously.
- Define and implement best practices for building, testing, and deploying scalable AI solutions, with emphasis on generative models and LLMs.
- Integrate RAG workflows, vector databases, and knowledge graphs for information retrieval and contextualization.
- Deploy and optimize LLMs and agent orchestration systems on public cloud (AWS) and on-premises environments.
- Drive business outcomes by architecting cloud-hosted generative AI solutions and collaborating with internal teams.
Requirements
Required
- 3–6 years overall technical experience; minimum 2 years hands-on with Generative AI and LLM technologies.
- 1+ year building agentic systems, workflow automation, or autonomous AI applications.
- Hands-on experience with agentic frameworks (AutoGen, LangGraph, CrewAI, Agency Swarm, or similar).
- Strong knowledge of workflow orchestration tools and patterns (Temporal, Airflow, Prefect, or similar).
- Expertise in OpenAPI standards, Agent-to-Agent (A2A) protocols, and Model Context Protocol (MCP).
- Experience designing multi-agent architectures with memory, planning, and tool-use capabilities.
- Knowledge of agent evaluation, testing frameworks, and observability patterns.
- Proven track record deploying and optimizing LLMs for inference in production; experience with LLM orchestration frameworks (LangChain, LlamaIndex required).
- Hands-on experience with Amazon Bedrock, SageMaker JumpStart, or other cloud-based LLM platforms.
- Expertise in RAG architectures, fine-tuning techniques, and prompt engineering.
- Deep understanding of vector databases (Pinecone, Weaviate, Milvus, ChromaDB) and knowledge graphs.
- Strong NLP and deep learning knowledge (Transformer models, LSTM, BiLSTM, CNN, BERT, GPT, T5).
- Proficiency with ML frameworks: TensorFlow, PyTorch, Hugging Face Transformers, scikit-learn.
- Strong programming skills in Python (required); familiarity with JavaScript/TypeScript or Node.js.
- Solid foundation in data structures, algorithms, and system design patterns.
- Hands-on MLOps/LLMOps experience including data pipelines, model training/refinement, validation, drift management, and serving.
- Experience with containerization (Docker, Kubernetes) and CI/CD for ML systems.
- Knowledge of monitoring, logging, and observability tools for production AI systems.
Preferred
- Experience with function calling, tool use, and external API integration within agent systems.
- Familiarity with reinforcement learning and agent training methodologies.
- Knowledge of semantic reasoning and planning algorithms (ReAct, Chain-of-Thought, Tree-of-Thoughts).
- Experience with graph databases (Neo4j, Neptune) and ontology design.
- Contributions to open-source AI/ML projects, publications, or patents in AI/ML.
Location & Employment Type
- Employment: Full-time
- Work model: Hybrid, Bengaluru
Notes
- The role expects working with both public cloud (AWS) and on-premises infrastructure and integrating with enterprise systems. The position emphasizes production readiness, observability, and scalable AI architectures.