LangChain CrewAI AutoGen GenAI LLM NLP Startup Transformers GetThingsDone AI Brief description of the vacancy We’re looking for a Gen AI Scientist to develop, scale, and support our LLM-driven autonomous platform. You’ll work with LangChain, AutoGen, CrewAI, and deploy open-source models (LLaMA, DeepSeek) in the Google Cloud. About the company 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, and Careem to derive actionable insights and deliver a better, real-time customer experience that drives sustainable growth. We are backed by top investors, including Neo, Sukna, Race Capital, Propeller, and Wamda, having raised $3.5m to date. Responsibilities Develop, scale, and support our LLM agentic system platform. Design and implement AI-driven autonomous workflows, enabling seamless human-AI interaction. Build and deploy open-source models in cloud environments, optimizing inference and serving costs. Improve and maintain data pipeline reliability and participate in on-call rotations. Debug and fix issues in ML pipelines, even when the cause is obscure. Collaborate with cross-functional teams to integrate AI models into production systems. Clearly articulate the work you’ve done and the impact you’ve made. We are early stage, so the work is dynamic and evolving.
Examples of additional challenges you might tackle: Make things work. Even the hardest things. Deploy AI models in scalable and cost-efficient ways. Optimize prompts, refine model outputs, and experiment with novel prompting strategies. Implement backend endpoints to bridge AI capabilities into our production stack. Label data and refine model training workflows. Hire and manage part-time annotators to improve data quality. Create quick prototypes using Dash/Streamlit to validate concepts. Own features end-to-end, from ideation to deployment. Be on-call for urgent AI model fixes or system failures. Qualifications Proficiency in Python and related libraries (e.g., NumPy, SciPy, pandas) is required. Strong production experience with at least one framework: LangChain, AutoGen, or CrewAI. Deep understanding of agentic systems, autonomous workflows, and LLM-based automation. Experience deploying and fine-tuning open-source models (e.g., LLaMA, DeepSeek) in the cloud. 5 years of hands-on experience in building, productionizing, iterating, and scaling AI-driven pipelines. Ability to take projects to completion, unblock yourself, and present results clearly and impactfully. Staying on top of recent trends, with hands-on experience in fine-tuning LLMs beyond API comparisons. Strong knowledge of software engineering, including building scalable web services and APIs. Experience developing full-stack applications, including database design, API development, admin panel creation, and monitoring systems. Experience with GCP is a big plus. DevOps experience is a big plus. Prompt engineering expertise and creative problem-solving mindset. Experience with processing multimodal data (text, images, audio) is a plus. Perks and Benefits: Fully Remote:
Work from anywhere with flexible hours. In-person Meetups and regular team-building remote events:
Enjoy occasional meetups and monthly game sessions. Generous Vacation:
Take time off when you need it. Growth Opportunities:
Continuous professional development and learning support. Dynamic Culture:
Be part of a fast-moving, high-impact team. Stock Options:
Get equity in our growing startup. Contacts
Log In Only registered users can open employer contacts.
#J-18808-Ljbffr