The Role As an AI/ML Technology Architect, you will lead the end-to-end design of agentic AI systems for the platform. You will own the architecture of multi-agent workflows, the orchestration backbone, agent communication patterns, evaluation frameworks, safety guardrails, and reusable design patterns that the engineering team will build against. This is a hands-on architect role, not a purely advisory or documentation-led role. The expectation is that you can design, review, prototype, debug, and guide implementation of production-grade agentic AI systems. You will work closely with founders, product leaders, engineers, and customer-facing teams to translate enterprise problems into scalable AI agent capabilities.

Key Responsibilities
• Architect production-grade multi-agent AI systems using LangGraph, AutoGen, CrewAI, or equivalent orchestration frameworks.
• Design stateful agent workflows
• Define agent capabilities for data discovery, profiling, scoring, enrichment, intelligence extraction, and contextual reasoning across enterprise data estate.
• Build and guide the design of structured data agents that can introspect live databases, infer schema meaning and generate ER-level understanding.
• Design document intelligence pipelines for large-scale extraction from unstructured data like PDFs, Word documents, emails, call transcripts, and semi-structured enterprise content using tools such as Azure Document Intelligence, AWS Textract, LlamaParse, or equivalent technologies.
• Architect vector database and retrieval pipelines, including chunking strategies, embedding model selection, metadata design, hybrid search, retrieval tuning, and domain-specific RAG patterns.
• Define agent evaluation methodology covering accuracy, precision, recall, recall@k, regression testing, drift detection, hallucination checks, and robustness testing for non-deterministic AI outputs.
• Establish AI safety and trust patterns, including semantic guardrails, jailbreak protection, prompt injection,



data exfiltration prevention, toxic output mitigation, policy-based response control, and secure tool-use design.
• Architect agent communication and message queuing patterns using RabbitMQ, Apache Kafka, or equivalent messaging platforms for scalable and resilient agent-to-agent/task communication.
• Lead technical reviews, mentor AI/ML engineers, validate architecture decisions, and own the technical quality of agent releases.
• Define reference implementations, reusable templates, coding patterns, and engineering standards for building agentic AI capabilities consistently across the platform.
• Partner with founders and product teams to translate business problems into transparent agent specifications, platform capabilities, and implementation roadmaps.
• Optimize LLM cost and latency through prompt caching, batching, token budgeting, model routing, model selection, and efficient prompt/context design.
• Stay current with the agentic AI and LLM ecosystem, including Anthropic, OpenAI, open-source models, LangChain/LangGraph, emerging evaluation tools, and enterprise AI deployment patterns. Must-Have Qualifications
• 12+ years of experience in software engineering, platform engineering, or applied AI/ML systems, with at least 4–5 years in AI/ML or applied ML solution development.
• Hands-on experience designing and shipping LLM-powered or agentic AI systems in production, not limited to notebooks, PoCs, or isolated demos.
• Demonstrated experience with multi-agent orchestration in production, using frameworks such as LangGraph, AutoGen, CrewAI, LangChain, or equivalent technologies.




• Proven experience building SQL or structured data agents that can connect to live databases, inspect schemas, infer semantic meaning, and generate relationship-level understanding.
• Strong working knowledge of RAG, vector databases, embedding models, chunking strategies, hybrid retrieval, metadata filtering, prompt engineering, and LLM evaluation. Deep knowledge of Pinecone, Milvus, or Qdrant, specifically around hybrid search (sparse + dense), reranking models (Cohere/BGE), and dynamic chunking strategies.
• Experience deploying open-source models (Llama, Gemma) via vLLM or Ollama to optimize throughput and cost.
• Experience implementing evaluation frameworks using tools such as RAGAS, LangSmith, Promptfoo, DeepEval, custom evaluation pipelines, or equivalent approaches.
• Strong Python skills and familiarity with the modern AI/ML engineering stack; ability to read, review, debug, and guide implementation-level code Good to Have
• Experience with knowledge graphs, ontologies, semantic data models, or enterprise metadata models.
• Open-source contributions in the AI/ML, data engineering, or agentic AI ecosystem.
• Experience with MLOps, LLMOps, model monitoring, observability, and production AI governance.
• Exposure to custom model training, fine-tuning, or domain adaptation, though the platform will primarily build on API-based and open-source LLMs. Why This Role Is Exciting You will be one of the most senior technical voices in the founding team. You will be defining the platform architecture, engineering patterns, AI safety controls, and agentic design principles from the ground up. The work will be hands-on, the autonomy will be high, and the impact will be highly visible. This role offers the opportunity to shape a venture-backed Infosys platform, influence early customer success, mentor the founding engineering team, and build enterprise-grade AI systems that can operate at real-world scale.

📌 AIML Technology Architect (Noida)
🏢 Infosys
📍 Noida