Affle
Website:
affle.com
Job details:
Designation: Senior SDE
Office Location: Bangalore
Role Overview
We are hiring an AI Enabler — a hands-on practitioner who ships AI-powered workflows, agents, and features into production. The ideal candidate is fluent in LLM application design, agentic frameworks, and modern AI tooling, and translates that fluency into measurable team velocity gains and product value. You will work cross-functionally with Engineering, Product, and Operations to identify high-leverage AI opportunities and build those solutions end-to-end.
What We’re Looking For
Someone who has shipped real AI into production — not just demos. You treat agents as narrow-role teammates with defined tools and stop conditions, and you’re as comfortable writing TypeScript middleware as crafting a system prompt. You’re energised by raising AI fluency across an entire team.
Primary Responsibilities
AI Feature Development & Agent Engineering
- Design, build, and ship LLM-powered features and bounded autonomous agents with observability, latency budgets, and fallback behaviour.
- Architect RAG pipelines — chunking, embedding selection, retrieval, and re-ranking — for internal knowledge bases and product surfaces.
- Build multi-step agentic workflows (LangGraph, LangChain, CrewAI, Claude Agent SDK) with scoped tool sets, structured outputs, and auditable side-effects.
AI Tooling & Developer Productivity
- Standardise AI-assisted engineering workflows — Claude Code, Cursor, GitHub Copilot, Augment Code — driving measurable feature delivery improvements.
- Author CLAUDE.md / AGENTS.md context files, shared system prompts, slash commands, and MCP integrations for the engineering team.
- Embed AI agents into code-review and test-generation loops with guardrails ensuring AI output meets engineering quality standards.
Cross-functional AI Enablement
- Partner with Product, Engineering, Data, and Operations to identify and scope high-leverage AI automation opportunities.
- Run structured evals and prompt experiments; maintain harnesses that track model quality and alert on regressions after upgrades.
- Document AI system designs, agent architectures, prompt libraries, and runbooks so the team can maintain and extend AI features independently.
Responsible AI & Operational Excellence
- Instrument LLM features with structured logging, cost tracking, and latency monitoring; own SLOs and incident response for AI-driven workflows.
- Apply output validation (Zod / JSON Schema) and human-in-the-loop checkpoints to manage hallucination risk in production.
Required Skills
AI & LLM Engineering (Core)
- 3+ years building and shipping LLM-powered features or AI agents in production.
- Working knowledge of Claude (Sonnet / Opus), GPT-4o, and/or open-source models (Llama, Hugging Face ecosystem).
- Proficiency with agentic frameworks: LangGraph, LangChain, LlamaIndex, or CrewAI; experience designing bounded, auditable agent workflows.
- Hands-on RAG experience: chunking, embeddings, vector stores (Pinecone, ChromaDB, pgvector), retrieval strategies, and re-ranking.
- Strong prompt and context engineering: system prompt design, structured output enforcement (JSON Schema / Zod), and prompt caching.
AI Developer Tooling
- Claude Code — context files (CLAUDE.md), slash commands, and agent guardrails.
- Cursor — AI-assisted coding and codebase-aware refactoring workflows.
- GitHub Copilot and / or Augment Code in daily development and code-review cycles.
- MCP (Model Context Protocol) — configuring or authoring MCP servers for agent context management.
Engineering Foundation
- Strong TypeScript / JavaScript and Node.js; Python for ML tooling is a plus.
- React or equivalent front-end framework; ability to build streaming, real-time AI-powered UIs.
- AWS or equivalent cloud (Lambda, API Gateway, S3, DynamoDB); REST, WebSockets, SSE, OAuth 2.0.
- Observability tooling applied to LLM systems: structured logging, cost tracking, latency dashboards.
Preferred
- SaaS, AI-native startup, AdTech, or FinTech product environment.
- Vector DB experience (Pinecone, Weaviate, Qdrant) and/or multi-modal model integration.
- Open-source AI contributions, published evals, or writing on LLM engineering practices.
Work Environment Details:
About Affle:
Affle is a global technology company with a proprietary consumer intelligence platform that delivers consumer recommendations and conversions through relevant Mobile Advertising. The platform aims to enhance returns on marketing investment through contextual mobile ads and also by reducing digital ad fraud. Affle powers unique and integrated consumer journeys for marketers to drive high ROI, measurable outcome-led advertising through its Affle2.0 Consumer Platforms Stack which includes Appnext, Jampp, MAAS, mediasmart, RevX, Vizury and YouAppi.
Affle 3i Limited successfully completed its IPO in India and now trades on the stock exchanges (BSE: 542752 & NSE: AFFLE). Affle Holdings is the Singapore-based promoter for Affle 3i Limited, and its investors include Microsoft, and Bennett Coleman & Company (BCCL) amongst others.
For more details, please visit:: www.affle.com
Click on Apply to know more.