AI Platform Engineer

Job Summary

Location and Schedule

• The role is listed as PAN India and remote.
• Core working hours are 11:00 am to 8:00 pm.
• The position may work from home and/or an office environment.

Build, Partner, and Operate

• Design, build, and operate AI platform services with clear API contracts, versioning, and SLOs.
• Write production Python and contribute to shared libraries, SDKs, and integration patterns.
• Instrument cost, latency, errors, quality signals, and audit logs for platform services.
• Own on-call rotation, author runbooks, and improve them after incidents.
• Onboard product AI features and provide technical support, integration guidance, and troubleshooting.
• Contribute to Architecture Decision Records and document technical tradeoffs.
• Set the operational bar for observability, alerting, incident response, and post-incident reviews.
• Evaluate vendors and make cost, quality, and reliability tradeoffs explicit.

Applied AI and RAG Engineering

• Build RAG-as-a-service capabilities covering ingestion, chunking, embeddings, retrieval quality, and hybrid search.
• Develop prompt templates, evaluation, versioning, and per-tenant customization.
• Implement guardrails, content safety, input filtering, output validation, PII redaction, and tool-use sandboxing.
• Develop agent frameworks and tool-use patterns for production workflows.
• Run domain-specific fine-tuning experiments and quality benchmarking.

Backend and Platform Engineering

• Build a multi-provider model gateway with routing, fallback, retry, and rate-limit logic.
• Develop prompt registries, versioning, rollout controls, shared libraries, SDKs, and API contracts.
• Design tenant isolation architecture and safe customer-data flows through platform services.
• Implement cost attribution and budget enforcement at the gateway layer.

MLOps and LLMOps Engineering

• Build observability for prompt and response tracing, cost per request, quality signals, and drift detection.
• Develop golden datasets, offline evaluations, LLM-as-judge patterns, and regression testing infrastructure.
• Create model deployment pipelines, including fine-tuned models where applicable.
• Establish alerting and SLO frameworks for AI services, including quality-regression alerts.
• Develop fine-tuning and RLHF pipelines when product-specific tuning is justified.

Required Qualifications

• Bachelor’s or Master’s degree in Computer Science, Engineering, or equivalent.
• At least five years of professional software engineering experience.
• At least six years building production distributed systems, ideally including internal developer platforms or API gateways at scale.
• At least five years in MLOps, LLMOps, ML platform engineering, or a hybrid DevOps and ML role at production scale.
• At least two years of hands-on production experience with LLM-based systems.
• Strong Python and one of Go or Java, including asynchronous patterns, backpressure, and rate limiting.
• Experience with multi-tenant systems, cloud-native infrastructure, Kubernetes, service mesh, Terraform, and CI/CD.
• Fluent English language skills.

Preferred Qualifications

• Domain experience in procure-to-pay, ERP integration, accounts payable, procurement, finance, or operations software.
• Experience at a product company or B2B SaaS company, ideally on an internal platform team.
• Contributions to open-source AI or ML infrastructure projects.
• Production experience with agent frameworks such as LangGraph, AutoGen, CrewAI, or custom orchestration.
• Experience on a founding platform team that shipped a v1 service for multiple internal customers.

About PairSoft