{"id":3407859,"url":"https://alion.io/job/rakuten-full-stack-engineer-ai","title":"Full - Stack Engineer - AI","company":{"id":13251,"name":"Rakuten","domain":"rakuten.co.in","url":"https://alion.io/company/rakuten","size_band":"11-50","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"Backend","role_family":"Backend","seniority":"senior","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":16500,"max_usd":39000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":168},"experience_years_min":5,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Amazon Redshift","optional":false},{"name":"Arize Phoenix","optional":false},{"name":"Embeddings","optional":false},{"name":"FastAPI","optional":false},{"name":"Google BigQuery","optional":false},{"name":"Hallucination","optional":false},{"name":"Hybrid Search","optional":false},{"name":"LangChain","optional":false},{"name":"Langfuse","optional":false},{"name":"LangGraph","optional":false},{"name":"LangSmith","optional":false},{"name":"LlamaIndex","optional":false},{"name":"LLM","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"OpenTelemetry","optional":false},{"name":"pgvector","optional":false},{"name":"Pinecone","optional":false},{"name":"Pydantic","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"React.js","optional":false},{"name":"Reranking","optional":false},{"name":"Snowflake","optional":false},{"name":"SQL","optional":false},{"name":"TypeScript","optional":false},{"name":"Weaviate","optional":false},{"name":"CI/CD","optional":true},{"name":"Fine-tuning","optional":true},{"name":"JavaScript","optional":true},{"name":"Knowledge Distillation","optional":true},{"name":"Model Distillation","optional":true},{"name":"PostgreSQL","optional":true},{"name":"Slack","optional":true},{"name":"WhatsApp","optional":true}],"status":"closed","first_seen_at":"2026-10-28T16:35:35Z","employer_posted_date":null,"last_verified_at":"2026-10-30T06:35:00Z","board_verified":false,"closed_at":"2026-10-30T06:35:00Z","days_open":1,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":1},"description":"We're hiring a Senior AI Engineer to own slices of Raptor's backend and AI layer, end-to-end retrieval, agent orchestration, evals, observability, and the admin tooling our internal users rely on. This role is ~70% Python backend and AI engineering and ~30% frontend (admin consoles, eval dashboards, and BU-facing configuration UIs). If you want to build chat UIs as your day job, this isn't the role. If you want to make production chatbots actually work and have the data to prove they do, read on.\n\nResponsibilities: \nBuild and own AI features end-to-end: retrieval, agent/router logic, prompt design, tool-calling, and post-processing from prototype to production traffic.\nImprove retrieval quality through chunking, embeddings, hybrid search, reranking, and grounded generation against BU knowledge bases. Measure hit rate, not vibes.\nRun the eval loop offline: eval harnesses, golden sets, LLM-as-judge graders, and regression suites. Every prompt or model change ships behind an eval delta.\nLLM observability instruments session-level traces, latency percentiles, retrieval hit rate, hallucination signals, intent misrouting, dead ends, and escalations.\nLatency and cost optimization: streaming, caching, model routing, batching, and prompt compression. Cost-per-session is a first-class metric.\nBackend services: Python services (FastAPI, async workers) that handle real production load with proper error handling, retries, and graceful degradation.\nSpec-driven development for non-trivial features: write a short design spec (problem, options, chosen approach, evaluations, and rollout) before writing code. We use AI coding tools heavily but reject vibe-coding: specs and evals are how we keep speed without losing the plot.\nPartner with PMs, conversation designers, and BU stakeholders to translate ambiguous product intent into a working system. Push back when the data says the proposal won't work.\nAdmin and eval tooling React/TypeScript surfaces for our team and BU stakeholders to configure flows, inspect sessions, review eval runs, and ship changes safely.\nGuardrails and AI safety input/output safety checks, PII handling, prompt-injection defenses, and refusal patterns appropriate to each BU context.\nOn-call and production support: debug live incidents, root-cause regressions, and own postmortems\n\nRequirements: \n5-8 years of software engineering experience, with at least 2 years building production LLM/AI applications that served real users (not demos).\nStrong Python backend experience with FastAPI or similar, async/await, Pydantic, background workers, and testing discipline.\nRetrieval/RAG in production vector stores (pgvector, Pinecone, Weaviate, or similar), hybrid search, and reranking.\nHands-on with at least one agent/orchestration framework (LangChain, LangGraph, LlamaIndex, or custom equivalent) and a clear point of view on when *not* to use multi-agent patterns.\nLLM evals golden sets, regression harnesses, LLM-as-judge, and gating releases on eval deltas.\nLLM observability: LangSmith, Langfuse, Arize, OpenTelemetry for LLMs, or equivalent homegrown tracing.\nSQL and warehouse data (BigQuery, Snowflake, Redshift, or similar) chatbot work is data work.\nWorking frontend skills in React + TypeScript sufficient to ship internal tooling and dashboards.\nSpec-driven development habit: comfortable writing short design docs and evals before code, using AI coding tools as accelerants rather than replacements for thinking.\nBachelor's degree in CS or engineering, or equivalent practical experience.\n\nNice to have: \nExperience shipping conversational AI for Japanese-language users or other non-English markets.\nExperience with messaging platforms (WhatsApp Business, Slack, in-app chat) or telephony/voice channels.\nFine-tuning, adapters, or distillation for cost/latency wins.\nPrompt versioning and feature-flagged prompt rollouts.\n\nTech you'll work with: \nBackend / AI: Python, FastAPI, async workers, LangChain/LangGraph, Frontier LLM APIs, pgvector / vector search, and Postgres.\nObservability & evals: LLM tracing tools, custom eval harnesses, OpenTelemetry.\nFrontend: React, TypeScript, a modern component library that is pragmatic, not religious.\nData: SQL on the warehouse and event instrumentation.\nInfra: Containerized services, CI/CD, on-call rotation.\nSkills\nAI, Artificial Intelligence, LLM, Python, Rag, Retrieval","description_format":"text","description_chars":4368,"description_truncated":false,"requirements":{"experience_years_min":5,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Artificial Intelligence","Marketplaces","Consumer Internet Groups"],"lifecycle":[{"event":"open","at":"2026-10-28T16:35:35Z"},{"event":"close","at":"2026-10-30T06:35:00Z"}],"visa":[],"liveness":null,"pay":null,"html_url":"https://alion.io/job/rakuten-full-stack-engineer-ai","json_url":"https://alion.io/job/rakuten-full-stack-engineer-ai.json","meta":{"generated_at":"2026-10-31T04:51:09Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":6770,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-01T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":13251},"rest":"https://alion.io/mcp/rest/get_company?id=13251"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Frakuten-full-stack-engineer-ai"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Frakuten-full-stack-engineer-ai"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Frakuten-full-stack-engineer-ai"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/rakuten-full-stack-engineer-ai\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Frakuten-full-stack-engineer-ai"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":3407859}},{"tool":"search_jobs","arguments":{"company":"rakuten.co.in","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":3407859},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}