Staff AI Platform Engineer - Inference & Agentic Systems

About the role

We are a small team of AI builders in Paytm Labs. As a Staff AI Platform Engineer you will work across inference and agentic systems, contributing to Paytm's AI inference platform and building the runtime, orchestration, and tooling for autonomous AI agents.

Key responsibilities

• Build and operate multi‑model serving across text, voice, code, and vision on shared infrastructure.
• Own the model lifecycle including download, deployment, monitoring, updates and swapping.
• Drive inference optimisation for latency, throughput and cost using quantisation, batching, caching and routing.
• Architect and build the Agentic AI platform – runtime, orchestration and developer tooling for autonomous agents.
• Design multi‑agent coordination systems and robust tool‑use infrastructure for safe API, database and service interactions.
• Implement workflow automation with guardrails, permissioning, sandboxing and human‑in‑the‑loop workflows.
• Develop evaluation, observability and debugging frameworks for agent behaviour.
• Define technical direction, standards and patterns for agentic systems across the organisation.
• Mentor engineers and collaborate with ML, product and security teams.

Required profile

• 8+ years of software engineering experience, with at least 3 years in AI systems or LLM applications.
• Strong understanding of LLM‑based agent architectures, tool use, multi‑step workflows and failure modes.
• Experience building highly reliable distributed systems and evaluating LLMs in production.
• Proficiency in TypeScript and Python, with willingness to work in both.
• Experience with modern LLM APIs or open‑source models and model serving frameworks.
• Understanding of distributed systems, cloud platforms (AWS, GCP) and containerised deployments.
• Strong knowledge of security risks in agentic systems.

Required skills

• TypeScript
• Python
• AWS
• GCP
• Kubernetes
• Temporal workflows
• Model serving (vLLM, TensorRT‑LLM, Triton)
• Distributed systems design
• LLM APIs