← All open roles

AI Integration Engineer

Location: India Eligible: India or USA Type: Full-time

Knowledge-base-grounded AI assistants, retrieval pipelines, prompt engineering at production scale. LLM cost and quality monitoring. Integration with client CMS, CRM, and support stacks.

OpenAI / Claude / AnthropicPythonVector DBs5+ years SWE2+ years AI

About the role

OpenSource Technologies is looking for an AI Engineer to help our clients move AI from prototype to production. You'll design, build, and ship LLM-powered features, RAG pipelines, and ML services that run reliably at scale — not demos, but systems real users depend on. You'll work directly with clients and our engineering team, owning problems end to end.

What you'll do

  • Build production AI features: LLM integrations, retrieval-augmented generation (RAG), agents, and evaluation pipelines.
  • Design and ship ML/AI services — from data pipelines and model selection to deployment, monitoring, and cost optimization.
  • Turn ambiguous client problems into scoped, measurable solutions with clear success metrics.
  • Write clean, tested, well-documented code and own it through to production and beyond.
  • Collaborate with full-stack, DevOps, and QA teammates to integrate AI into existing apps and workflows.
  • Stay current with the fast-moving AI landscape and bring practical, cost-aware recommendations to the table.

What we're looking for

  • 3+ years of software engineering experience, with at least 1–2 years building AI/ML or LLM-powered systems.
  • Strong Python; comfortable with production codebases (testing, code review, CI/CD).
  • Hands-on experience with LLM APIs (OpenAI, Anthropic, or similar) and frameworks for RAG/agents.
  • Solid understanding of embeddings, vector databases, prompt design, and evaluation.
  • Experience deploying services to the cloud (AWS/GCP/Azure), with an eye on latency, reliability, and cost.
  • Clear communicator who can explain trade-offs to both engineers and non-technical stakeholders.

Nice to have

  • Experience with fine-tuning, model serving, or MLOps tooling.
  • Full-stack familiarity (TypeScript/Node, React) to integrate AI end to end.
  • Background in a client-services or consulting environment.
  • Contributions to open-source AI/ML projects.

Why OST

  • Work on production AI for real clients across multiple industries — variety, ownership, and impact.
  • A senior team that values clean engineering, direct communication, and shipping things that actually work.
  • Flexible, remote-friendly setup with the autonomy to do your best work.

How to apply

Send a short note about a production AI system you've shipped (what it did, your role, and one hard trade-off you made) along with your resume via the Apply button. We respond to every legitimate application within 5 business days.