Company: Innodata Inc.
Salary: Not provided
Location: , United States
• Prototype LLM + retrieval pipelines with safety and filtering.
• Operate knowledge graph/vector DBs (Pinecone, Weaviate) and manage embeddings.
• Build FastAPI services for search, recsys, and memory.
• Design resilient systems with caching, retries, observability
. • Run data pipelines for large-scale indexing and embeddings.
• Capture personalization signals (search, chat, purchase).
• Optimize for low-latency APIs & high-throughput pipelines.
• Collaborate with research and product on evaluation and UX.
• Strong Python (FastAPI, async/await, Redis, PostgreSQL).
• 1-3 years of hands-on experience with LLM prompting, RAG, embeddings, vector search.
• Comfort with APIs, distributed systems, caching, observability.
• Familiarity with GCP/AWS/Azure or similar cloud services, Docker, Git, CI/CD.
• Clear communicator, self-driven, team player.
• TypeScript/Node.js/javascript (NestJS), React/Next.js.
• Familiarity with FAST API, Streamlit and similar frameworks.
• Recommender systems exposure.
• Embedding model evaluation skills.
• We are an equal opportunity employer committed to fostering an inclusive, respectful, and diverse workplace.
• We welcome and encourage applications from individuals of all backgrounds and are dedicated to employment equity and building a team that reflects the diverse communities in which we live and operate.
• In accordance with the Accessibility for Ontarians with Disabilities Act (AODA), we are committed to providing accommodations throughout the recruitment and selection process.
job post pulled from jsjobs
Get TypeScript jobs in your inbox
Copyright © ReadingWaters 2025.