Added
2 hours ago
Type
Full time
Salary
Salary not provided

Related skills

python langchain llamaindex openai anthropic

📋 Description

  • Design and maintain production-grade LLM pipelines (RAG, prompts, parsing).
  • Develop AI features for spend categorization, document extraction, and Q&A.
  • Implement output validation, fallbacks, and confidence scoring.
  • Evaluate AI frameworks (LangChain, LlamaIndex, OpenAI, Anthropic) and select tools.
  • Establish prompt versioning and evaluation as models/data evolve.
  • Design and maintain vector search pipelines for semantic search.

🎯 Requirements

  • Bachelor's degree in CS/Engineering or related field, or equivalent practical experience.
  • 5+ years software engineering, with at least 3 years AI/ML in production.
  • Hands-on experience deploying LLM-powered apps using OpenAI, Anthropic, or Cohere in production.
  • Design/operate RAG pipelines with chunking, embeddings, and vector DBs (Pinecone, Weaviate, pgvector).
  • Strong Python for AI/ML; familiarity with LangChain, LlamaIndex, or equivalents.
  • Experience with ML model serving: REST or gRPC endpoints, input/output validation, latency budgeting, monitoring.
  • Backend fundamentals: REST APIs, PostgreSQL, async, cloud (AWS, GCP, or Azure).
  • Observability: structured logging, distributed tracing, dashboards for AI system health.
  • Preferred: fintech or regulated industry experience.
  • Preferred: ML lifecycle tools (MLflow, Weights & Biases, Vertex AI, SageMaker).
  • Preferred: real-time data streaming (Kafka, Kinesis) and startup experience.
Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Related Engineering Jobs

See more Engineering jobs →