--- title: 'Applied AI Engineer - Agent Intelligence & Retrieval at Littlebird' canonical: 'https://feeny.ai/job/applied-ai-engineer-agent-intelligence-retrieval-littlebird-remote-7wgmp8ptzdbb' type: 'job' last_seen: '2026-09-09' --- # Applied AI Engineer - Agent Intelligence & Retrieval at Littlebird - **Company:** Littlebird - **Location:** Remote - **Employment:** full-time - **Work type:** remote - **Posted:** 2025-11-20 - **Last confirmed live:** 2026-09-09 - **Apply:** https://jobs.gem.com/littlebird/am9icG9zdDpftgr_F1AcbaNAqQWn-rTX ## Job description ## Role Overview We're seeking an Applied AI Engineer to join our fast-paced team to design, develop, and implement new features for [Littlebird](https://www.joinlittlebird.com/), our AI teammate for Mac and Android (Windows soon). We're building a personal AI that connects your entire digital life, protecting your focus from clutter and surfacing what you need, the moment you need it. Check out the recent [TechCrunch news on our $11M seed funding](https://www.linkedin.com/feed/update/urn:li:activity:7442288049939533825) and what users are saying about the product. We're a small, async-first team that values craft and ownership. Our engineers live at the intersection of genuine research curiosity and production discipline: you'll push the frontier in areas like conversational inference, ranking, and sentiment analysis, then wrestle those ideas into systems that are fast, lean, and built to scale. ## The Role This role is about making our agent smarter, faster, and more reliable. You will live in the core of our AI, obsessing over the quality of our retrieval, the precision of our ranking, and the logic of our agent. Some of the hard problems you'll solve: Master the Art of Retrieval & Re-ranking: Our current hybrid search pipeline is functional but will need to scale with customer growth. You will own its evolution. - - Solve the "Broad Query" Problem: How do you make retrieval work just as well for "what did I do last week?" as it does for a specific, targeted question? This involves query analysis, decomposition, and potentially multiple retrieval strategies. - Optimize the Ranking Stack: You'll experiment with and productionize new re-ranking models to crush our latency bottlenecks. You'll fine-tune our ranking strategy to better blend sparse and dense retrieval signals. - Develop Intelligent Pruning: How do you shrink the context passed to the LLM by 80% without losing the critical 1% of information that leads to the right answer? You'll design and test sophisticated context pruning and summarization techniques. Engineer Better Agentic Reasoning: Our agent uses a multi-step, tool-calling approach to solve problems. Debugging and improving it is a core challenge. - - Context Engineering: You'll become an expert in "prompt-level" performance, figuring out the optimal way to structure and present context to the LLM to minimize hallucinations and improve reasoning. - Debugging Complex Agentic Flows: You'll be a detective, tracing the root cause of agent failures through layers of tool calls, context retrieval, and LLM responses to understand where things went wrong and how to fix them. What we're looking for: - Strong OOP programming skills and prior experience writing production software in python, Typescript, or C++ - A deep, intuitive understanding of information retrieval and modern RAG pipelines. You've likely built a few from scratch. - Hands-on experience with vector databases, hybrid search, and re-ranking models. - An experimental, data-driven mindset. You're comfortable running A/B tests, analyzing metrics, and iterating quickly to improve performance. - A pragmatic approach. You're focused on shipping tangible improvements to the AI's quality, not just chasing SOTA benchmarks. ## Benefits - Remote-friendly work environment - Collaborative team culture - Opportunity to shape infrastructure decisions - Competitive compensation packages including stock and health benefits, paid time off, and parental leave. 401k options for all US-based employees. - Flexible working hours across multiple time zones - We love to hear when birds chirp! ## About Littlebird ## Company Overview - **One-liner**: Littlebird is a full-context AI assistant for macOS that continuously observes your screen and meetings to deliver answers and automate tasks based on your actual work context. - **Entity Type**: Private (Seed stage – $11M raised) - **Headquarters**: San Francisco, California, United States - **Founded**: 2024 - **Founders**: Alap Shah, Alexander Green, Naman Shah ## Core Business - **Primary industry/industries**: AI-powered productivity / Context-aware AI assistants - **Target customers**: Individual professionals, knowledge workers, and teams using macOS (B2C, also potentially B2B via enterprise-grade security) - **Mission or purpose statement**: (From website) “Organize your life and work… an AI that knows and understands what you're working on, so you can stay focused on what matters.” ## Products & Services - **Littlebird (macOS App)**: A desktop AI assistant that runs in the background, reading the active window on your screen and transcribing meetings to build a private memory of your work. No manual setup or copy/pasting required. It can answer questions, draft emails/docs in your voice, take meeting notes, and automate daily routines (e.g., morning briefings, weekly summaries). Available for Apple Silicon, macOS 13+. Companion apps for iOS and Android allow querying on the go. - **Paid Plans**: Free tier with limited usage; paid plans starting at $20/month for higher limits and features like image generation. - **Integrations**: Optional integrations with hundreds of tools across categories: project management (Notion, Linear), design (Canva, Miro), developer tools (Cloudflare, PlanetScale), CRM (Intercom, Outreach), finance (Mercury, Ramp), meetings (Calendly, Granola), marketing (Klaviyo), analytics (Mixpanel), knowledge (Guru, Google Drive), email/calendar (Gmail, Outlook, Apple Calendar). Integrations are optional; the core product works by observing the screen. ## Market Standing - **Valuation/Market Cap**: Not publicly disclosed (private company) - **Key Metric**: Total funding $11M (Seed round, March 2026) - **Notable Investors/Partners**: Led by Lotus Studio; participants include Lenny Rachitsky, Scott Belsky, Gokul Rajaram, Justin Rosenstein, Shawn Wang, and Russ Heddleston. - **Growth Signals**: LinkedIn reports 30 employees (+1600% YoY) as of early 2026; offices in San Francisco and Newark; distributed across 7 countries (India, US, Poland, Pakistan, Ukraine). 84% of users say it saves at least half a day per week (per company claim). Rapid LinkedIn follower growth (+5122% yearly). ## Competitive Advantages - **Full-context memory without setup**: Unlike general AI assistants that require manual copying/pasting, Littlebird automatically understands the current project, document, and conversation by reading the screen. This makes responses faster and more personalized. - **Native macOS background operation**: Works on Apple Silicon with minimal friction, observing the active window and running meeting transcription via system audio. - **Privacy-first design**: Users control what is seen/kept; data encrypted at rest and in transit (AWS); SOC 2 certified, GDPR and CCPA compliant. No data sold or used to train models. - **Proven founding team**: Co-founders previously sold Sentieo (AI platform for investors) to AlphaSense; also built health-food company Thistle. One co-author of the “Citrini” paper that impacted tech stocks. ## Strategic Focus - **Scaling the user base**: Currently free to download with a paid subscription model to drive adoption among knowledge workers. - **Expanding platform support**: Already available on Mac, Windows (likely in beta or announced), plus mobile companion apps. - **Deepening integrations**: The product relies on optional app connections to provide deeper context; likely expanding integration library and automation capabilities (Routines feature). - **Enterprise adoption**: Emphasis on security compliance (SOC 2, GDPR) suggests a push into B2B sales and team/enterprise plans. ## Why Work Here - **High-growth startup**: 30 employees, huge YoY headcount increase, well-funded seed round. Opportunity to shape product and culture early. - **Hybrid Work Policy**: “Hybrid Workspace” as per Built In – employees combine remote and on-site work, with typical time on-site mentioned (likely SF office). - **Culture & Perks**: No specific perks listed, but emphasis on privacy, automation, and building for power users. Founder background in multiple successful startups indicates a fast-moving, engineering-centric environment. - **Current Openings** (as of mid-2026): Product Analyst, Senior Social Media Manager, Senior Backend Engineer, Social Media & GTM Intern, Product Manager – suggesting both engineering and go-to-market teams growing. ## Sources 1. [littlebird.ai/about-us](https://littlebird.ai/about-us) 2. [builtin.com/company/littlebird-ai](https://builtin.com/company/littlebird-ai) 3. [littlebird.ai](https://littlebird.ai) 4. [linkedin.com/company/littlebirdai](https://linkedin.com/company/littlebirdai) 5. [techcrunch.com](https://techcrunch.com/2026/03/23/littlebird-raises-11m-to-capture-context-from-your-computer-so-you-can-query-your-data) ## Other roles at Littlebird - [Founding Sales Leader](https://feeny.ai/job/founding-sales-leader-littlebird-san-francisco-8asr2hrz3cpx) — San Francisco, CA - [Creator in Residence](https://feeny.ai/job/creator-in-residence-littlebird-remote-6cctbk4demjb) - [Product Manager](https://feeny.ai/job/product-manager-littlebird-bengaluru-h9ev0j3s8dbm) — Bengaluru, India - [Senior Social Media Manager - Consumer](https://feeny.ai/job/senior-social-media-manager-consumer-littlebird-remote-mt3reerwtk3s) - [Senior Backend Engineer](https://feeny.ai/job/senior-backend-engineer-littlebird-remote-ajgp4w2p8bns) - [Product Analyst](https://feeny.ai/job/product-analyst-littlebird-remote-jtvn6r0bdr8g) - [Senior / Staff AI Engineer (Systems & Architecture)](https://feeny.ai/job/senior-staff-ai-engineer-systems-architecture-littlebird-remote-7vxtrsgys1aa)