AI Engineer

About Ravian AIRavian AI is building device-native AI systems that can think, decide, and act on behalf of users. Our platform goes beyond web-based agents, enabling true end-to-end automation directly on devices. We’re working with enterprises and consumers to unlock productivity and decision intelligence at scale.The RoleYou will design and build production-grade, multi-agent AI systems and the backends that power them. You’ll work across FastAPI services, WebSocket event streams, orchestration logic (Autogen/LangGraph), and device execution layers to deliver agents that complete real tasks—autonomously, safely, and repeatably.What you’ll do (Responsibilities)Design & build backends: Develop high-performance APIs with FastAPI, implement WebSockets for streaming I/O, and own service-level reliability (timeouts, retries, backoff, circuit breakers).Agentic orchestration: Implement multi-agent workflows using Autogen, LangGraph, or similar frameworks; handle tool calling, memory, state, guardrails, and safe-actions.Productionize AI: Turn models + prompts into idempotent workflows with input validation, schema contracts, evaluation harnesses, and offline/online metrics.Observability & safety: Ship deep tracing, structured logs, and red-teaming hooks. Build guardrails to prevent bad actions and ensure reversible operations.Performance engineering: Reduce latency, control costs, and design fallbacks (models, tools, or policies) for robustness under failure.Collaboration: Partner with product, design, and customers to scope problems, define SLAs, and iterate quickly from prototype → pilot → production.Quality bar: Write crisp tests, automate CI/CD, and maintain documentation others can rely on.Must-Have Qualifications (Requirements)3–5 years of software/AI engineering in production environments.Strong backend skills with FastAPI (or similar), WebSockets, async Python, and at least one cloud(AWS/Azure/GCP).Hands-on with multi-agent systems using Autogen, LangGraph, or equivalent—not just hello-world notebooks.Proven record of having built and shipped AI projects/products used by real users (internal or external).Solid understanding of LLM tooling (prompting, tool-use, RAG, evals, safety/guardrails).Comfortable with data models, queues, caches, relational/NoSQL storage, and containerization.Nice-to-Have (Bonus)Experience with device control (browser automation, OS-level actions, mobile/desktop app automation).Knowledge of retrieval systems, vector stores, and evaluation frameworks.Experience with observability stacks (OpenTelemetry, Prometheus/Grafana, ELK).Prior publications, OSS contributions, or GitHub repos demonstrating deep work.We are NOT consideringFreshers.Candidates withApplicants who haven’t shipped AI systems (toy demos/ usual projects don’t count).Candidates whose background is only classical ML model training without production agentic experience or have deep learning experience.Tech you’ll touchPython, FastAPI, WebSockets, Autogen, LangGraph, Celery/Queues, SQL/NoSQL, Docker, AWS (Lambda/ECS/S3), OpenTelemetry, CI/CD.How we hireIntro call (30 mins): What you’ve shipped.Technical deep dive (60–90 mins): Walkthrough of a system you built, live reasoning on agentic design trade-offs.Practical exercise (take-home or live): Build or critique a small multi-agent flow time line 2-3 days.Founder discussion: Product sense, speed, and ownership.References & offer.Apply - exactly like this (don’t skip)Send an email to and # mention bothwith the subject:Subject: Application — AI Engineer — Your NameAttach/Include:Cover letter (1 page max) addressing:A production AI system you shipped, your role, scale, and business impact.Multi agent system you have buildWhy device-native agents excite you.Resume (PDF) with links to GitHub/Portfolio.GitHub (top 2–3 repos that show relevant code).Papers published (if any) or technical blog posts.Salary expectation (fixed).Clarify if you identify as Data Scientist or ML Engineer with production multi-agent systems experience.Note: If your background is limited to training classical ML models without production agentic work, please do not apply.Compensation ₹8–12 LPA (INR) based on experience and fit.Potential performance-based upside.NOTE : Please ensure you must have a clear understanding of Ravian AI, its mission, and the applications it builds before applying or engaging further. Familiarity with the company’s device-native AI systems, which enable end-to-end automation and decision intelligence, is essential for alignment and meaningful contribution .