P

PairSoft

Automates procurement, AP, and document management

AI Platform Engineer

Applied Machine LearningConfirmed live in the last 24 hours
Full-timeRemote in IndiaNo salary listed

About the Job

Requirements

  • A Bachelor's or Master's degree in Computer Science, Engineering, or equivalent is required.
  • At least 5 years of professional software engineering experience with a strong production track record is required.
  • At least 6 years building production distributed systems is required, ideally including internal developer platforms or API gateways at scale.
  • At least 5 years in MLOps, LLMOps, ML platform engineering, or a hybrid DevOps plus ML role at production scale is required.
  • Hands-on experience with observability tools for LLM systems such as LangSmith, Langfuse, Braintrust, Arize, or comparable tools is required.
  • Working knowledge of evaluation methodology for LLM systems, including benchmark design, LLM-as-judge, and human review workflows, is required.
  • Working fluency in the modern LLM ecosystem is required, including OpenAI or Anthropic APIs, an orchestration framework such as LangChain or LlamaIndex, a vector database, and an observability tool.
  • At least 2 years of hands-on production experience with LLM-based systems, including prompt engineering, RAG, evaluation, or LLM infrastructure, is required.
  • Strong Python and one of Go or Java are required, along with comfort with asynchronous patterns, backpressure, rate limiting, and writing production code rather than only notebooks or scripts.
  • Experience designing multi-tenant systems with hard isolation guarantees is required.
  • Cloud-native depth on Azure or AWS is required, including Kubernetes, service mesh, infrastructure as code with Terraform, and CI/CD.
  • Experience shipping model updates safely in production, including canaries, shadow evaluation, and rollback triggers, is required.
  • Comfort with the full ML lifecycle, including training pipelines, serving infrastructure, monitoring, and cost management, is required.
  • A strong grasp of AI security fundamentals, including PII handling, tenant isolation, and prompt injection basics, is required.
  • Ability to communicate technical decisions clearly in asynchronous writing is required; the role is distributed across time zones and cannot rely solely on synchronous meetings.
  • Fluent English language skills are required.

Responsibilities

  • Design, build, and operate services in the central AI platform, with clear API contracts, versioning, and service-level objectives from day one.
  • Write production Python for AI services and contribute to shared libraries, SDKs, and integration patterns for product teams.
  • Instrument services with cost tagging per request, latency and error metrics, quality signals, and audit logs.
  • Own the on-call rotation for the AI platform services built; author runbooks and improve them after incidents.
  • Work directly with product engineering leads across product lines to onboard their AI features onto the central platform.
  • Provide technical support, integration guidance, and troubleshooting to product teams consuming platform services.
  • Contribute to Architecture Decision Records, challenge decisions when appropriate, and document tradeoffs.
  • Set operational practices for observability, alerting, incident response, and post-incident reviews.
  • Own vendor evaluation for tools in the role's specialization and run bakeoffs when choices are unclear; make cost, quality, and reliability tradeoffs explicit.
  • Contribute to the AI security posture through PII handling, tenant isolation, prompt injection defense, and audit logging within services.
  • Build retrieval, prompt, and guardrail systems that make LLM output suitable for customer-facing production use.
  • Build a RAG-as-a-service platform covering ingestion, chunking, embedding, retrieval quality, and hybrid search.
  • Develop prompt engineering systems at scale, including templates, evaluation, versioning, and per-tenant customization.
  • Build guardrails and content safety capabilities, including input filtering, output validation, PII redaction, and tool-use sandboxing.
  • Implement agent frameworks and tool-use patterns as agent workflows move into production across product lines.
  • Run domain-specific fine-tuning experiments and quality benchmarking.
  • Own the model gateway, orchestration layer, service mesh, and data plumbing connecting platform components.
  • Build a multi-provider model gateway with routing, fallback, retry, and rate-limit logic.
  • Maintain a prompt registry, versioning, and rollout controls such as canaries and feature flags.
  • Build shared libraries and SDKs for product teams, including API contracts, versioning, and deprecation strategy.
  • Design tenant isolation architecture for safe customer-data flow through platform services.
  • Implement cost attribution and budget enforcement at the gateway layer.
  • Own observability capabilities for prompt and response tracing, cost per request, quality signals, and drift detection.
  • Build evaluation infrastructure including golden datasets, offline evaluations, LLM-as-judge patterns, and regression testing.
  • Develop model deployment pipelines, including pipelines for fine-tuned models where applicable.
  • Establish alerting and service-level objectives for AI services, treating quality regression as a first-class alert.
  • Build fine-tuning and reinforcement learning from human feedback pipelines when product-specific tuning is justified.

Desired Qualifications

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

About the Company

PairSoft

Automates procurement, AP, and document management

PairSoft provides automated procurement and document management solutions for medium to large organizations across industries like healthcare, higher education, hospitality, manufacturing, distribution, non-profit, and professional services. It offers procurement automation, accounts payable (AP) automation, and document management that work together to streamline purchasing processes. The platform supports end-to-end workflow—from catalog and supplier management to approvals and invoice processing—typically delivered on a subscription basis with pricing tailored to a client’s size and needs, plus implementation support and training. Its software aims to move organizations from paper-based processes to a paperless system, offering complete visibility and analytics to help users make better purchasing decisions, save time, and reduce costs while boosting productivity and collaboration among teams.

Company size
51-200
Company stage
Not listed
Total funding
Not listed
Headquarters
Miami, FL
Founded
1997

Recently Posted Jobs

Explore more opportunities at PairSoft

See more jobs