Key Skills and Responsibilities (A, SA, M-level):

- Hands-on experience to Google ADK or CoPilot Studio in building AI Agents (or any tool such as CrewAI, Autogen for building agents)
- Hands-on working knowledge in defining and configuring prompts, instructions, tools, reasoning, guardrails and other similar concepts in AI Agent development
- Strong experience with RAG pipelines, Vector DBs, tokenization, and prompt engineering
- Hands-on experience in creating and maintaining Python libraries, utilize LangChain, Hugging Face, OpenAI API, or local models
- Very strong experience with developing RESTful APIs in Python using frameworks like FastAPI and integrate third-party services, UI components and APIs
- Hands-on working with Docker-based deployments, and leveraging GitHub for code repo and version control is MUST
- Interpret microservices design principles and cloud computing basics
- Strong communication skills and articulation skills

Key Skills and Responsibilities (SM, AD -level):

- Architect and govern enterprise-grade multi-agent AI systems using LangGraph, Google ADK, CoPilot Studio, CrewAI, or AutoGen - defining reusable orchestration patterns, agent lifecycle standards, and cross-agent communication frameworks
- Define and own organizational standards for prompt engineering, agent instructions, tool definitions, memory management, guardrails, and reasoning frameworks - driving consistency across delivery teams and engagements
- Design scalable RAG architectures including chunking strategies, embedding model selection, vector DB topology (Pinecone, Weaviate, pgvector etc), retrieval optimization, and hybrid search patterns at enterprise scale
- Lead evaluation, selection, and integration strategy for LLM models (OpenAI, Claude, Gemini, Hugging Face, local/fine-tuned models) and Python-based AI libraries including LangChain and LangGraph - establishing reusable frameworks, agentic workflow patterns, and inner-source libraries across teams
- Build, maintain, and evolve internal AI/agentic platforms - including agent runtimes, orchestration layers, tool registries, and shared infrastructure - ensuring reliability, extensibility, and adoption across delivery teams and client engagements
- Architect RESTful and event-driven API ecosystems using FastAPI and similar frameworks; define integration patterns with third-party services, enterprise APIs,



and UI layers at a platform level
- Own platform-level decisions on containerization (Docker, Kubernetes), CI/CD pipelines, and GitOps practices - establishing DevSecOps standards and deployment topology for AI workloads in production
- Design cloud-native, microservices-based AI solution architectures (GCP, Azure, or AWS) - encompassing scalability, resilience, observability, cost optimization, and service mesh patterns
- Leverage and advise on hyperscaler-native AI/ML offerings including managed model endpoints, vector search services, AI pipelines, and MLOps tooling across GCP (Vertex AI), Azure (AI Foundry, Azure OpenAI), and AWS (Bedrock, SageMaker) to accelerate platform delivery and reduce undifferentiated engineering effort
- Lead architecture review boards, mentor Managers and Senior Associates, engage senior client stakeholders, and translate complex AI architecture decisions into clear business value narratives

Key Skills

Key Skills and Responsibilities (A, SA, M-level):

- Hands-on experience to Google ADK or CoPilot Studio in building AI Agents (or any tool such as CrewAI, Autogen for building agents)
- Hands-on working knowledge in defining and configuring prompts, instructions, tools, reasoning, guardrails and other similar concepts in AI Agent development
- Strong experience with RAG pipelines, Vector DBs, tokenization, and prompt engineering
- Hands-on experience in creating and maintaining Python libraries, utilize LangChain, Hugging Face, OpenAI API, or local models
- Very strong experience with developing RESTful APIs in Python using frameworks like FastAPI and integrate third-party services, UI components and APIs
- Hands-on working with Docker-based deployments, and leveraging GitHub for code repo and version control is MUST
- Interpret microservices design principles and cloud computing basics
- Strong communication skills and articulation skills

Key Skills and Responsibilities (SM, AD -level):





- Architect and govern enterprise-grade multi-agent AI systems using LangGraph, Google ADK, CoPilot Studio, CrewAI, or AutoGen - defining reusable orchestration patterns, agent lifecycle standards, and cross-agent communication frameworks
- Define and own organizational standards for prompt engineering, agent instructions, tool definitions, memory management, guardrails, and reasoning frameworks - driving consistency across delivery teams and engagements
- Design scalable RAG architectures including chunking strategies, embedding model selection, vector DB topology (Pinecone, Weaviate, pgvector etc), retrieval optimization, and hybrid search patterns at enterprise scale
- Lead evaluation, selection, and integration strategy for LLM models (OpenAI, Claude, Gemini, Hugging Face, local/fine-tuned models) and Python-based AI libraries including LangChain and LangGraph - establishing reusable frameworks, agentic workflow patterns, and inner-source libraries across teams
- Build, maintain, and evolve internal AI/agentic platforms - including agent runtimes, orchestration layers, tool registries, and shared infrastructure - ensuring reliability, extensibility, and adoption across delivery teams and client engagements
- Architect RESTful and event-driven API ecosystems using FastAPI and similar frameworks; define integration patterns with third-party services, enterprise APIs, and UI layers at a platform level
- Own platform-level decisions on containerization (Docker, Kubernetes), CI/CD pipelines, and GitOps practices - establishing DevSecOps standards and deployment topology for AI workloads in production
- Design cloud-native, microservices-based AI solution architectures (GCP, Azure, or AWS) - encompassing scalability, resilience, observability, cost optimization, and service mesh patterns
- Leverage and advise on hyperscaler-native AI/ML offerings including managed model endpoints, vector search services, AI pipelines, and MLOps tooling across GCP (Vertex AI), Azure (AI Foundry, Azure OpenAI), and AWS (Bedrock, SageMaker) to accelerate platform delivery and reduce undifferentiated engineering effort
- Lead architecture review boards, mentor Managers and Senior Associates, engage senior client stakeholders, and translate complex AI architecture decisions into transparent business value narratives

📌 Gen AI opening for Chennai, Bangalore, Hyderabad
🏢 Arminus
📍 Chennai