RAG jobs

Founding Engineering role with early IC focus (first 3–6 months) to build a multi-modal AI agent product (voice + SMS + email). Responsibilities include building real-time voice systems (streaming audio, low latency, turn-taking), SMS and email automation wit…

AirOps is the runtime marketing teams at Ramp, Chime, Carta, and Rippling use to earn citations in responses from ChatGPT, Claude, and Perplexity. It provides orchestrated LLMs, RAG, JavaScript/Python code steps, evals, and human-in-the-loop systems. Backed b…

Building an executive voice engine (Eve), a multi-agent AI system that learns how a leader thinks and produces content indistinguishable from what they'd write. Role includes full AI stack and product: agent orchestration, evals, RAG, prompt chaining, model t…

Starbridge is building an AI platform that turns large-scale public and enterprise data into reliable sales insights. The role offers huge ownership and product impact. Backend Engineer: build enterprise integrations, large-scale scraping and parsing pipeline…

Form AI is an AI fluency/integration startup for executives and their teams. They build tailored AI applications for how clients work. Typical engagements start with clients describing a workflow that consumes their time; the engineer scopes with the client a…

We aggregate marketing and financial data into dashboards. Heavy backend focus on ETL, data pipeline, modeling, and normalization. Front end is straightforward React. Looking for skills in Python, React, FastAPI, Postgres, ClickHouse, Spark, Kafka, AWS, MCP, …

We’re hiring an AI Engineer to build and ship production AI systems (not research prototypes). Startup experience is a must; you should have shipped fast in a small team, owned systems end-to-end, and be comfortable with ambiguity. Responsibilities include ow…

Hiring a junior AI-native developer to extend an agentic AI copilot embedded in Architect AI, a portfolio-management web app. Work includes text-to-SQL over financial schemas (holdings, transactions, performance), RAG over internal docs, action tools, and dep…

F-1 STEM OPT through Feb 2028 (no sponsorship needed). 4 yrs production GenAI experience: AWS Bedrock, RAG (92% recall, HIPAA), LangGraph multi-agent copilots shipped to production, QLoRA/LLaMA 2 fine-tuning, LangChain/LlamaIndex, Python, Docker/K8s. Co-autho…

Curie is a telehealth platform combining clinical expertise with AI to deliver personalized, accessible care. Team includes ex-founders, clinicians, and engineers from Stanford, Harvard, UCLA, Berkeley, and AWS. The role is for an AI Engineer to own the micro…

Remote Full-Stack Engineer (Python/React) role building production AI systems focused on real-world workflows, data pipelines, and integrating LLM-based systems into usable products. Work includes designing backend systems and APIs, building and scaling LLM w…

Build an AI system for patent search into a production multi-tenant SaaS product. Work includes multi-tenant org accounts, roles and audit, knowledge graph integration (OriginTrail), RAG and semantic search pipelines, and making core product decisions. Seekin…

We are building an AI platform for credit unions. A variety of tools (third party integrations + RAG) backed by multiple LLM options, including OLMo, running in our own AWS infrastructure. Small team (CTO is the poster and the first technical hire) so the can…

Looking for experienced engineers to build and scale infrastructure and data platforms for a Berlin asset management fund. The team is building AI-driven investment infrastructure to support high alpha targets. Responsibilities include designing large-scale d…