GenAI Tech Lead: Structured Insights

GenAI Tech Lead — Structured Insights, Anomalies & Novelties

Short Description

As the Tech Lead for Structured Insights & Detection, you’ll own the algorithms and systems that turn messy, multi-channel feedback into reliable structured insights, flexible anomaly detectors, and novelty discovery—and deliver trustworthy alerts to product & CX teams. You’ll collaborate directly with engineers, directors, the CTO, and other tech leads to turn ambitious prototypes into a rock-solid product used by brands like Grubhub, Booking, Dropbox & Uber.

About Anecdote

Anecdote is an innovative, AI-first startup revolutionizing how companies analyze customer feedback. Our AI-powered platform consolidates feedback from app reviews, support chats, surveys, and social media into a single, easily accessible space. This enables companies like Grubhub, Dropbox, Fubo, Booking.Com and Uber to derive actionable insights and deliver a better, real-time customer experience that drives sustainable growth.

We’re backed by Neo, Sukna, Race Capital, Propeller, and Wamda.

What you’ll actually do

50% Build — design & ship

• Structured extraction from unstructured text (and other modalities) using schema-driven pipelines, tool-use, and retrieval.
• Hybrid anomaly detection blending classical time-series (Prophet/statsmodels/Kats) with LLM-aware, contextful detectors (seasonality, spikes, step-changes, drift).
• Novelty discovery: embedding-based clustering & drift, topic surfacing, and LLM summarization of emerging themes with deduplication and evidence links.
• Alerting & scoring: severity/impact ranking, de-noising, suppression/cool-downs, routing, and feedback loops.

25% Architect & scale

Own reliability, latency, and cost, design online/offline eval harnesses, canarying, and SLAs. Operate GPUs/accelerators where needed. Own on-call for your area.

15% Collaborate

Pair with back-end & front-end to wire detectors/extractors into ticketing, voice, and analytics stacks (APIs, webhooks, real-time streams). Partner with PMs/CX to evolve taxonomies, schemas, and guardrails.

10% Align & showcase

Gather requirements from CX leads, demo new capabilities to execs & customers, and document impact in plain English with precision/recall, alert quality, and cost metrics.

What makes you a great fit

• Startup hacker mindset: you respect no boundaries, self-start from zero, and carry work from first prototype to production finish line. 🛠️
• AI-native dev tools in your DNA: Cursor, v0, Claude Code (and similar) are daily drivers.
• 7–10 years building production ML/back-end systems; 2+ years leading while coding.
• Expert Python; strong back-end chops (FastAPI, gRPC, Postgres, pub/sub/streams).
• Hands-on with time-series analysis (decomposition, change-point, forecasting) and modern LLM approaches (prompting, tools, RAG).
• Fluency with at least one agent framework (ADK preferred) and building RAG pipelines.
• Track record translating business problems into shipped ML features—and explaining results clearly.

Perks and bonuses

• Remote-first freedom & flexible hours 🏠
• Regular off-sites & monthly virtual game nights 🎉
• Unlimited vacation (minimum 20 days encouraged) 🏝️
• Learning budget for conferences, courses & books 📚
• Startup equity in a rapidly growing market 💼