Member of Technical Staff

THE ROLE Nirva is building the first AI fashion accessory for your mind: a necklace or bracelet that privately listens only to the wearer to enable proactive journaling, emotion tracking, and life coaching. Think Oura Ring for your mind. Backed by Lightspeed and South Park Commons, recognized at CES within 90 days of founding, and launching in the U.S. this fall. Co-founders bring backgrounds from Meta Reality Labs (Quest, Ray-Ban glasses) and the fashion industry. We're looking for a engineering talents to build Nirva's intelligence layer: the systems that turn real-life context into memory, reflection, journaling, and emotionally aware companionship. This is not a generic AI wrapper role. You'll design how Nirva understands a person over time: how it retrieves context, summarizes life moments, reasons over memory, structures personal data, calls tools, evaluates outputs, and turns messy real-world signals into experiences that feel useful, personal, and alive. You'll work directly with the founding team to build AI-native product systems from the ground up. WHAT YOU'LL OWN Build AI agent experiences across chat, memory, tools, structured context, prompts, and model orchestration Design how Nirva retrieves, summarizes, ranks, and injects personal context so the product feels genuinely personalized over time Build systems for memory-backed conversation, journaling, daily recaps, emotional insights, and proactive AI experiences Create pipelines that transform transcripts, user context, events, and memories into high-quality product experiences Improve model behavior through prompt iteration, structured outputs, test cases, evals, and debugging real user-facing failures Work across LLMs, embeddings, retrieval, ranking, summarization, classification, tool use, and agentic workflows Partner closely with product and design to make AI feel warm, trustworthy, specific, and emotionally intelligent, not generic or gimmicky Move quickly across ambiguous AI, product, and engineering problems without waiting for perfect specs WHAT WE'RE LOOKING FOR Must-haves 3+ years of strong engineering experience, with evidence of shipping real products used by real users Hands-on experience building AI-native product systems with LLMs: agents, memory, context engineering, retrieval, tool use, structured outputs, prompting, evals, and handling model variability Strong product engineering instincts: you turn model capability into polished user-facing experiences Strong debugging mindset for AI systems: you can identify why outputs fail, design tests, improve prompts or pipelines, and evaluate quality systematically Comfortable with ambiguous, subjective, human-centered AI problems where "good" is not easy to measure High ownership: you identify what needs to happen and drive it to shipped quality Energized by 0-to-1 work, fast iteration, and early-stage startup intensity Strong product taste for consumer products that need to feel personal, trustworthy, and emotionally resonant Based in San Francisco and able to work in person Strong signals (nice-to-haves) Voice/audio AI: speech-to-text, text-to-speech, streaming audio, VAD, diarization, audio preprocessing, latency optimization, or speech event detection Memory systems, personal knowledge graphs, context stores, or long-term personalization Mobile or iOS product engineering Consumer AI, journaling, coaching, wellness, or companionship products Eval frameworks, data flywheels, fine-tuning, or human feedback loops Experience spanning backend, AI infrastructure, and user-facing surfaces COMPENSATION Competitive salary plus meaningful equity for an early stage role. Health, dental, and vision included, along with direct access to the founders and a real shot at building your next company. #J-18808-Ljbffr