7 days ago
Pune, IndiaStaff+
Responsibilities
- Build production AI and agentic workflows from PRD and architecture through implementation, evaluation, release, and production iteration.
- Design agent orchestration involving tool and API invocation, planning, routing, state, memory, retries, fallbacks, timeouts, and human-in-the-loop checkpoints.
- Own retrieval capabilities including corpus onboarding, parsing, chunking, embeddings, hybrid search, reranking, metadata filtering, query transformation, permissions, freshness, and incremental indexing.
- Select, tune, route, and evaluate models based on quality, latency, and cost, while managing prompts, structured outputs, context strategies, and versioned evaluation artifacts.
- Build evaluation harnesses with golden datasets, offline evaluation, calibrated LLM-as-judge workflows, regression suites, online quality monitoring, and structured feedback.
- Design and maintain reusable SDKs, shared services, templates, reference implementations, documentation, and partner-facing engineering standards.
- Integrate AI workflows with enterprise ERP, CRM, support, services delivery, knowledge, and data platforms.
- Implement production engineering practices including caching, batching, streaming, model tiering, graceful degradation, observability, tracing, cost telemetry, quality dashboards, infrastructure as code, secret handling, and testing.
- Participate in operational support, incident reviews, remediation, code and design reviews, and mentoring of subsequent engineers and partner teams.
Requirements
- 6+ years of professional software engineering experience, including 2+ years building and operating production LLM or GenAI systems with real users and operating costs.
- Excellent Python and working competence in at least one additional language such as TypeScript, Go, or Java.
- Demonstrated production experience building, measuring, and improving RAG or hybrid search systems.
- Experience with agent orchestration frameworks such as LangGraph, LlamaIndex, Semantic Kernel, Google ADK, Strands, or CrewAI, plus judgment about when not to use a framework.
- Strong AWS and/or GCP experience, including managed AI services, compute, serverless, networking, IAM, and managed data services.
- Experience with API design, enterprise integration, OAuth 2.0/OIDC, service-to-service authentication, and delegated or on-behalf-of access.
- Experience with containerization, infrastructure as code using Terraform, CDK, or an equivalent, CI/CD, and rigorous testing.
- Ability to define measurable quality criteria for subjective tasks, evaluate results, and make cost- and latency-aware design decisions.
- Clear written communication, including design notes, documentation, and status reporting, plus comfort with ambiguity and shifting priorities.
- Preferred experience includes production-scale vector or hybrid search, evaluation and observability tooling, multi-tenant SaaS, ERP/manufacturing/supply-chain data, classical ML and MLOps, fine-tuning or model serving, internal platforms or SDKs, and open-source AI engineering contributions.
Benefits
- Health and well-being programs supporting work-life balance.
- Opportunity to join a growing business entering a new phase of expansion and transformation.
- Collaborative culture with supportive colleagues and an emphasis on idea-sharing over hierarchy.
- Growth and development opportunities.
- Compensation packages based on experience and desired skill set.
Tech Stack
Categories
About QAD, Inc.
QAD builds cloud-based ERP and supply chain software for manufacturing companies, with offerings like QAD Adaptive ERP and the Redzone Connected Workforce platform, sold primarily by subscription with professional services. Its products target mid-market firms across automotive, industrial, food & beverage, life sciences, and consumer goods, embedding workflow and shop-floor capabilities. Founded in 1979 and headquartered in Miami, QAD is privately held and owned by Thoma Bravo.