Paytm
Senior AI Engineer
Toronto, Canada · Senior
Sponsorship not specifiedDetected 26 days ago
PythonReactAWSAzureDockerKubernetesTemporalMachine LearningAirflowLLMsRAGAgentic AIAI OrchestrationAccessibilityCommunication
About the role
- There's a wide gap between an agent that works in a demo and one that works across millions of live transactions.
Responsibilities
- Own deployments end-to-end: discovery, build, integration, activation, and the tuning that earns trust and adoption.
- Lead pilots and demos, drive adoption, and clear blockers before they stall a rollout.
- Build safe tool-use infrastructure across APIs, databases, and services, with permissioning, sandboxing, and human-in-the-loop.
- Ship SDKs, patterns, and reusable blueprints so internal teams build and deploy agents fast.
- Design and run rigorous evals: measure quality, catch regressions, and feed results back into the system.
- Build observability, tracing, and guardrails that prove agents are safe and keep them safe as models and data drift.
- mentor engineers and partner with ML, product, and security.
- Set technical direction and standards for agentic systems; mentor engineers and partner with ML, product, and security.
Requirements
- Proficiency in Python across a broad stack - pipeline, agent, service, and instrumentation.
Nice to have
- Cloud AI/ML services (AWS SageMaker / Bedrock, Azure ML / Azure OpenAI)
- MCP or agent communication standards
- agent evaluation and observability tooling.
- Model serving (vLLM, TensorRT-LLM, Triton), fine-tuning, quantization, or LoRA.
- Workflow orchestration (Temporal, Airflow, Prefect) for AI workloads
- voice / multimodal / edge inference.
- Testing and verification for non-deterministic AI systems.
- Go Big or Go Home!
Skills
- Build agentic systems
- Architect agentic systems - reasoning, planning, tool use, memory, multi-agent coordination - that run real workflows with guardrails.
- Make it reliable
Benefits
- Own the multi-model inference your agents depend on (text, voice, code, vision) - latency, throughput, and cost.
Company info
- Tackle greenfield problems alongside internal teams and customers - scope ambiguous needs and build agents from scratch that fit how they actually work.
This listing is sourced directly from Paytm's careers page and normalized into a canonical job model.