Senior AI Platform Engineer

Overview

Senior AI Platform Engineer to be the technical cornerstone of PAR's newly formed AI Platform team, designing, building and operating a production-grade, multi-tenant AI Platform on AWS for building and running AI agents and agentic workflows across PAR Restaurant product lines.

What you'll do

• Design, build and operate a production-grade, multi-tenant AI Platform on AWS using LLM orchestration services, tools and libraries.
• Build production GenAI microservices (e.g. FastAPI) and stateful multi-agent workflows, selecting the orchestration pattern (model-driven, graph-based etc.) based on auditability, latency and complexity requirements.
• Design and operate an automated content ingestion pipeline covering content upload, chunking, embedding model selection, vector storage and OpenSearch Serverless indexing, exposing knowledgebase retrieval as a self-service capability for all product teams.
• Build and maintain platform APIs and developer tooling, including MCP-compatible tool interfaces, real-time streaming APIs (SSE / WebSocket) and agent configuration SDKs.
• Own internal AI SDK ergonomics for agent-authoring engineers and application-backend engineers consuming the streaming invocation API.
• Build and maintain the Platform Onboarding Copilot (Slack-integrated).
• Produce clear, actionable technical documentation and architectural decision records (ADRs), and present platform strategy to non-technical stakeholders.
• Own the platform observability stack, including tools for fetching metrics and distributed traces auto-provisioned on every agent deployment, an LLM eval suite that gates CI/CD on quality regressions, and per-tenant cost attribution with spend alerting.
• Define quality bars and eval suites per agent class, so no agent reaches production without a documented, passing score threshold.
• Design multi-tenant isolation from day one, including namespace isolation, tenant_id injection and policy-as-code enforcement ensuring no cross-brand data or context pollution.
• Own the policy-as-code library for PAR-specific policy sets and ensure platform compliance with SOC 2 Type II, PCI DSS, GDPR and CCPA; author and maintain the GDPR deletion pipeline.
• Define and implement content safety guardrails, with grounding checks and content filtering mandatory for all customer-facing agents.
• Act as quality and cost-economics gatekeeper for all agents entering pre-production, running standardised eval suites and validating inference cost-per-run against approved thresholds.
• Collaborate with DevOps through a defined infrastructure contract and build a version promotion pipeline (e.g. GitHub Actions).

What you'll need

• 7–8 years of hands-on Machine Learning / AI Engineering experience.
• At least 3 years focused on production GenAI or LLM systems.
• Master's in Computer Science, Machine Learning, or a closely related field.
• Demonstrated experience designing and building multi-tenant, production-grade ML platforms or developer-facing AI infrastructure.
• Proven track record of shipping ML systems end-to-end, from architecture and deployment through operational observability, eval pipelines and cost management.
• Deep AWS experience: API Gateway, Amazon Bedrock AgentCore, Lambda, S3, CloudFront, EKS (Kubernetes + IRSA), OpenSearch Serverless, KMS, SageMaker, Step Functions, WAF, PrivateLink, CloudWatch, IAM.
• GenAI and LLM frameworks: LangChain, LangGraph, LlamaIndex, Hugging Face Transformers, OpenAI API, Anthropic API, AWS-native GenAI services.
• RAG and knowledge systems: vector stores (FAISS, ChromaDB, Pinecone, Weaviate) and OpenSearch Serverless, designing end-to-end ingestion, chunking, embedding and hybrid retrieval pipelines.
• ML Ops: MLflow (tracking, model registry, job orchestration), Databricks (PySpark, Delta Lake, notebooks), automated retraining workflows.
• Expert-level Python (FastAPI / Flask / Django); proficient TypeScript / Node.js (Express / NestJS); clean code, OOP and scalable architecture.
• Data stores: Delta Lake, Elasticsearch, Redis, NoSQL, columnar stores (Databricks, BigQuery).
• CI/CD and DevOps collaboration: GitHub Actions; familiarity with Terraform Cloud / HCP Terraform workflows; container-native development on EKS.
• Observability and monitoring: CloudWatch (metrics, logs, dashboards, alarms), distributed tracing (AWS X-Ray or equivalent), LLM evaluation frameworks (LangSmith, Ragas, or similar).
• Security and policy: policy-as-code frameworks, IAM policy design, multi-tenant namespace isolation, PCI DSS and GDPR technical controls.
• Exceptional written and verbal communication, able to explain policy-as-code enforcement to a security auditor and a RAG pipeline to a product manager in the same meeting.
• Strong collaboration instincts, measuring success by adoption, not just uptime.
• Emerging leadership skills: mentoring engineers, leading design reviews, or owning a technical domain end-to-end.
• Comfort with ambiguity in a greenfield platform with real architectural decisions to make.
• Flexibility to occasionally collaborate with teams in California (PST) and Toronto (EST) for cross-time zone syncs.

Nice to have

• Familiarity with restaurant, hospitality, or retail domains.
• Experience building or fine-tuning domain-specific LLMs or embedding models.
• Experience building enterprise-scale Text-to-SQL applications.
• Multi-agent orchestration and A2A protocols; familiarity with workflow automation tools (e.g. n8n) for MCP-compatible tool interoperability.
• Experience building LLM-specific observability beyond standard infra monitoring, e.g. hallucination tracking, groundedness scoring, per-session cost and cost attribution.
• Contributions to open-source ML or GenAI projects.
• Experience with policy-as-code frameworks for cloud access control at scale.
• Familiarity with defining and executing sprint plans, technical roadmaps, weekly standups and quarterly OKRs for a team.
• Prior people management or tech lead experience.

Details

• Position location: Gurugram / Jaipur, India (Hybrid).
• Reports to: Director of AI and Analytics.
• Interview process: phone screen with Talent Acquisition Team; video interview with the Technical Teams (via MS Teams/F2F); video interview with the Hiring Manager (via MS Teams/F2F).