19 Nov
|
Recrew AI
|
Delhi
Role: AI Engineer (Backend & AI Systems)
Function: Engineering / AI & Backend Systems
Location: Delhi (Onsite)
Type: Full-time
Industry: Media Production, Broadcast Media, Online Media
About Company The company is one of India's largest private FM radio networks. It reaches over 40 million listeners weekly across 49 cities, 1,000+ towns, and 50,000 villages.
Active since 2006 and headquartered in Delhi, it is owned by a major Indian media conglomerate. It is the only private FM station broadcasting from Jammu & Kashmir, with an international presence in Singapore and Bhutan.
Its digital platform extends the brand into curated music, lifestyle, and news content for urban and rural audiences. With a team of 740 and a culture rooted in creativity and community, engineers here build products that reach millions of real listeners at scale.
Position Overview
This role sits at the core of the company's AI product push — building backend systems and LLM-powered features that serve listeners, creators, and advertisers. You'll take business-level ideas and ship them as production-grade AI products: designed, instrumented, and costed. The work spans RAG pipelines, agent workflows, recommendation logic, and the backend infrastructure that keeps all of it running reliably.
Role & Responsibilities
- Translate business requirements into concrete AI system designs — components, data flows, model choices, latency budgets, and cost estimates
- Build and maintain LLM-powered features in production: structured prompting, RAG pipelines (chunking, embeddings, hybrid search, reranking), and multi-step agent workflows using LangGraph or equivalent
- Design backend services with clear API boundaries, queuing, caching,
and vector + SQL storage — with explicit failure modes and SLOs
- Instrument everything: offline evals, online A/B tests, and dashboards tracking quality, latency, and cost-per-request
- Collaborate with product and business stakeholders to scope AI use cases — and confidently push back when AI is the wrong tool
- Keep indexes fresh, monitor retrieval quality, and iterate on model routing decisions (OpenAI, Anthropic, open-source) based on real production data
Must Have Criteria
- 3–5 years of software engineering experience with strong backend and system design fundamentals
- Hands-on experience shipping LLM-powered features to production — prompting, RAG, or agent workflows that were monitored and costed, not just demoed
- Proficiency with LangGraph or a comparable agent/workflow orchestration framework
- Experience designing and operating backend services on AWS (EC2, Lambda, S3, or equivalent) with CI/CD pipelines
- Working knowledge of vector databases and hybrid search (embedding + keyword) for retrieval use cases
- Demonstrated ability to take a business-level ask and independently produce a technical design
Nice to Have
- Experience building recommendation systems or video/streaming platform backends
- Familiarity with eval tooling such as Ragas, LangSmith, or Braintrust
- Exposure to voice/audio AI — STT, TTS, or audio processing pipelines
- Background in media, radio, advertising, or content-tech domains
- Fine-tuning experience with open-source LLMs
What We Offer
- Work on a rare combination of broadcast scale and digital product innovation
- Onsite role in Delhi, embedded with product and business teams from day one
- Chance to grow into a lead/architect track as the AI team scales
📌 AI Engineer (Delhi)
🏢 Recrew AI
📍 Delhi