Ovii Job Board

AI Engineer

Meraki Labs

Bengaluru, India • Onsite - Bengaluru, India • Full-Time • 1-5 years

Posted 2026-08-17 Tech & Engg

Apply on employer site

Job Description

Ovii's Interpretation of the Role

Meraki Labs' Fermi team seeks an AI Engineer to design, build, and ship production‑grade AI tutoring workflows. The role blends fast‑paced feature delivery with deep engineering quality in an onsite Bangalore environment.

Role Snapshot

  • Build end‑to‑end AI tutoring pipelines
  • Ship production‑ready AI services
  • Own feature lifecycle from PRD to monitoring
  • Collaborate with product, design, and education teams
  • Optimize latency, cost, and reliability
  • Work onsite in Bangalore

Must-Have Requirements

  • Python
  • FastAPI/Flask
  • Docker
  • LLM framework (OpenAI SDK, LangChain, Haystack)
  • Python development
  • Building services with FastAPI/Flask
  • LLM workflow engineering

Nice-to-Have Signals

  • Computer Science background
  • Multimodal pipelines (voice)
  • Latency & cost optimization techniques
  • Computer Science education
  • Strong project or open‑source track record
  • Computer Science or equivalent

Work Setup

  • Location: Bangalore, India
  • Work mode: ONSITE
  • Employment type: Full-Time

Not Specified in JD

  • Visa sponsorship
  • Salary range
  • Remote eligibility
  • Education requirement
  • Certifications
  • Relocation
  • Notice period
  • Travel
  • Security clearance
  • Coding test
  • Portfolio
  • GitHub
  • Writing sample
  • Cover letter

What You'll Likely Work On

  • Build core AI tutoring flows such as hinting, step‑by‑step guidance, and misconception detection
  • Implement answer evaluation, grading, and feedback loops
  • Develop retrieval and grounding pipelines (content ingestion, chunking, embedding, re‑ranking)
  • Create personalization mechanisms using student memory, progress signals, and difficulty adaptation
  • Build multimodal pipelines for images/diagrams and optionally voice
  • Optimize latency and cost via caching, batching, streaming, and fallbacks
  • Establish observability and safety guardrails (traces, logs, metrics, prompt/version tracking)
  • Own features from PRD through implementation, deployment, monitoring, and iteration

Good Fit If You Have

  • Thrives in fast‑paced, ambiguous environments
  • Takes ownership without waiting for direction
  • Values engineering quality through tests, evals, and instrumentation

Skills

  • Python
  • FastAPI / Flask
  • Docker
  • LLM frameworks (OpenAI SDK, LangChain, Haystack)
  • Prompt engineering & retrieval
  • Production observability (traces, logs, metrics)
  • Latency & cost optimization
  • Multimodal pipelines (images, voice)