Project Role : Large Language Model Architect
Project Role Description : Architect large language models (LLM) that can process and generate natural language. Design neural network parameters, trained on large quantities of unlabeled text data.
Must have skills : Large Language Models (LLMs), Virtual Agents, Generative AI
Good to have skills : NA
Minimum
15 year(s) of experience is required
Educational Qualification : 15 years full time education
Summary:
Agent Runtime Reports to: Engineering Manager, Platform Core (EM1)
Experience: 10–14 years (12–14 years) Location: Bangalore / US (flexible)
ROLE OVERVIEW:
This is the tech lead role for Pod 2, the most technically complex surface of the platform. You will design and own the agent runtime the system that assembles enterprise context, executes agent invocations, enforces guardrails, manages session state, and produces the trace records that make every agent run observable and auditable.
Roles & Responsibilities:
- Design and own the Agent Lifecycle Manager implementation context assembly pipeline, guardrail enforcement, session and memory management, and invocation tracing
- Lead Pod 2's three LLM/agent engineers, evaluation engineer, session and memory engineer, and observability engineer
- Define the pre-deployment evaluation harness
- Own the runtime's reliability contract latency budgets, failure modes, circuit breaker patterns
- Partner with the Lead Architect on orchestration framework selection and LLM API integration patterns
- Define observability standards for agent invocations
Ideal Profile:
- Has built and operated production LLM or agentic systems at scale understands context window management, prompt architecture, and token budget optimization
- has designed distributed systems with strong reliability requirements has led a small technical team.
