AI/ML Architect
Description
Job Description - AI/ML Architect (Agentic AI / Generative AI)
Position: AI/ML Architect Agentic AI & Generative AI
Experience: 10+ Years
Location: Noida
Work Mode: Work From Office (WFO)
Employment Type: Full-Time
Open Positions: 1
NOTE - WE ARE ONLY LOOKING FOR IMMEDIATE JOINERS WHO CAN WORK FROM NOIDA LOCATION.
Position Summary
We are looking for an experienced AI/ML Architect with 10+ years of overall experience and strong expertise in designing, architecting, and implementing enterprise-grade AI/ML and Generative AI solutions.
The ideal candidate must have strong hands-on and architectural experience in Agentic AI, LangGraph, Multi-Agent Systems, MCP (Model Context Protocol), A2A (Agent-to-Agent), DAG-based workflow orchestration, and LiteLLM.
The candidate will be responsible for defining enterprise AI architecture, designing scalable agentic frameworks, establishing technical standards, and leading the development and deployment of intelligent AI-driven applications.
This role requires someone who can translate complex business requirements into robust AI architectures, lead engineering teams, make critical technology decisions, and ensure AI solutions are secure, scalable, cost-efficient, and production-ready.
Key Responsibilities
1. AI/ML Architecture & Solution Design
- Define and own end-to-end architecture for enterprise AI/ML, Generative AI, and Agentic AI solutions.
- Design scalable, modular, and reusable AI architectures and frameworks.
- Establish architectural standards, design patterns, and best practices for AI application development.
- Evaluate emerging AI technologies, foundation models, frameworks, and tools.
- Drive architectural decisions related to model selection, orchestration, infrastructure, integration, and deployment.
- Translate business requirements into technical architecture, solution designs, and implementation roadmaps.
2. Agentic AI & LangGraph Architecture
- Architect and lead the development of complex, stateful, multi-step agentic workflows using LangGraph.
- Design enterprise-grade multi-agent systems with planning, reasoning, memory, decision-making, and autonomous execution capabilities.
- Define reusable agent architectures, state management strategies, and workflow orchestration patterns.
- Design and implement agent-to-agent (A2A) communication and collaboration frameworks.
- Establish patterns for human-in-the-loop workflows, agent supervision, error recovery, and execution control.
- Optimize agent performance, reliability, scalability, and execution efficiency.
3. MCP, A2A & Workflow Orchestration
- Define architecture and implementation standards for MCP servers and clients.
- Architect secure integration of AI agents with enterprise applications, databases, APIs, and external tools using MCP.
- Design distributed and DAG-based workflow orchestration frameworks.
- Establish standards for agent communication, tool discovery, authentication, authorization, and context management.
- Implement interoperable agent architectures using A2A communication protocols.
- Ensure reliable execution, fault tolerance, and monitoring of complex agent workflows.
4. LLM Architecture & Model Management
- Design centralized LLM access and abstraction layers using LiteLLM.
- Architect multi-provider LLM integrations involving OpenAI, Azure OpenAI, Anthropic, Gemini, and other foundation models.
- Implement intelligent model routing, fallback mechanisms, load balancing, and cost optimization.
- Define model selection strategies based on latency, accuracy, security, and business requirements.
- Establish standards for prompt engineering, structured outputs, function calling, and agent memory.
- Drive implementation of RAG pipelines, embeddings, semantic search, and vector database integrations.
5. Enterprise AI Integration & Development
- Architect Python-based AI services, APIs, and microservices.
- Define integration patterns for AI solutions with enterprise platforms, databases, and third-party applications.
- Design scalable backend systems using Python, FastAPI, REST APIs, and distributed services.
- Guide implementation of AI-powered enterprise applications and intelligent automation solutions.
- Ensure seamless integration between AI components and existing enterprise technology ecosystems.
6. Security, Governance & Production Readiness
- Define AI security, governance, and responsible AI implementation standards.
- Establish guardrails for prompt injection, data leakage, unauthorized tool execution, and unsafe agent behaviour.
- Design secure authentication, authorization, data privacy, and access control mechanisms.
- Implement LLM evaluation, testing, observability, tracing, and monitoring frameworks.
- Define standards for model performance evaluation, hallucination management, and response quality.
- Drive production readiness, reliability, disaster recovery, and operational excellence.
7. Technical Leadership
- Lead and mentor AI/ML engineers, senior developers, and technical teams.
- Conduct architecture reviews, design discussions, and technical evaluations.
- Provide technical direction throughout the complete AI solution lifecycle.
- Collaborate with business stakeholders, product teams, engineering teams, and leadership.
- Own technical delivery, architecture quality, and resolution of complex engineering challenges.
- Stay updated with emerging Agentic AI frameworks, LLM technologies, and enterprise AI architecture trends.
Mandatory Technical Skills
AI/ML & Generative AI
- 10+ years of overall experience in software engineering, AI/ML, data science, or related technology domains.
- Strong experience in designing and implementing AI/ML and Generative AI solutions.
- Deep understanding of LLMs, foundation models, NLP, and machine learning concepts.
- Strong experience building enterprise-grade LLM-powered applications.
Agentic AI & LangGraph
- Strong hands-on and architectural experience with LangGraph.
- Experience designing complex, stateful, multi-agent workflows.
- Expertise in agent planning, reasoning, memory, tool calling, and orchestration.
- Experience with agent-to-agent (A2A) communication and multi-agent architectures.
MCP & Workflow Orchestration
- Strong practical experience with MCP (Model Context Protocol).
- Experience architecting MCP servers, clients, and enterprise tool integrations.
- Strong understanding of DAG-based workflow orchestration.
- Experience designing reliable, distributed, and event-driven workflows.
LLM Management & Integration
- Hands-on experience with LiteLLM, including model abstraction, routing, fallback, and multi-provider integration.
- Experience integrating OpenAI, Azure OpenAI, Anthropic, Gemini, or similar LLM providers.
- Strong understanding of RAG, embeddings, vector databases, prompt engineering, and structured outputs.
Programming & Backend Technologies
- Strong Python programming and software architecture skills.
- Experience with FastAPI, REST APIs, microservices, and backend development.
- Knowledge of PostgreSQL, Redis, vector databases, and distributed systems.
Cloud & Deployment
- Experience architecting and deploying AI solutions on AWS, Azure, or GCP.
- Knowledge of Docker, Kubernetes, CI/CD, and cloud-native architectures.
- Experience with production deployment, monitoring, scaling, and performance optimization.
Good to Have
- LangChain, LlamaIndex, CrewAI, AutoGen, or similar agentic frameworks.
- Knowledge Graphs and Graph-based RAG.
- LLM evaluation frameworks such as RAGAS, DeepEval, or similar tools.
- AI observability and tracing tools such as LangSmith, Langfuse, or equivalent.
- Experience with AI guardrails, responsible AI, and enterprise AI governance.
- Experience with event-driven architecture and distributed computing.
- Experience designing enterprise AI platforms and reusable AI accelerators.
Core Technology Stack
Python | AI/ML | Generative AI | Agentic AI | LangGraph | MCP | A2A | DAG | LiteLLM | LLMs | RAG | Multi-Agent Systems | Vector Databases | FastAPI | Microservices | AWS / Azure / GCP | Docker | Kubernetes
Candidate Screening Important Requirements
- LangGraph is mandatory: Candidates must have hands-on experience designing and implementing LangGraph-based solutions in professional projects.
- MCP experience: Must have practical experience developing or integrating MCP servers/clients and enterprise tools.
- Multi-Agent Architecture: Must demonstrate experience designing multi-agent systems and A2A communication.
- LiteLLM: Must understand model abstraction, routing, provider integration, and LLM management.
- Architecture Ownership: Must have independently designed and owned AI solution architecture, not just contributed to development.
- Production Experience: Must have experience deploying and managing enterprise-grade AI applications in production.
Candidates with only theoretical knowledge, certifications, training, or academic projects in LangGraph, MCP, or Agentic AI will not meet the core requirement.
Preferred Candidate Profile: A hands-on AI/ML Architect who can independently own enterprise AI architecture while providing technical leadership and guiding engineering teams from solution design through production deployment.
Contact -
Call / What's App Resume - 9718978697
Email - siddharth.mathur@moptra.com
Manager - Global Talent Acquisition
MOPTRA INFOTECT PVT LTD
Skills
- Agentic AI
- AI
- Anthropic
- API
- Authentication
- AutoGen
- Automation
- AWS
- Azure
- CI/CD
- Cloud
- Cloud Native
- CrewAI
- Data Science
- Design Patterns
- Distributed Computing
- Distributed Systems
- Docker
- Embeddings
- Event Driven Architecture
- FastAPI
- GCP
- Generative AI
- Kubernetes
- LangChain
- Langfuse
- LangGraph
- LangSmith
- LiteLLM
- LlamaIndex
- LLM
- Machine Learning
- MCP
- Microservices
- NLP
- Observability
- OpenAI
- PostgreSQL
- Prompt Engineering
- Python
- RAG
- Redis
- REST
- Semantic Search
- Solution Design
- Vector Databases
- Workflow Orchestration
Sign in to read and join the discussion.