Deploy LLM based production grade solutions.
Fine-tune and adapt State of the art LLMs for specialized data extraction tasks.
Develop innovative prompt engineering strategy and systems to maximize reliability and performance on confidential business documents.
Solve Engineering challenges that come along with LLM solutions, such as high latency, non-deterministic output, etc.
Implement and scale data processing pipelines that can process high volumes of complex documents with high accuracy and efficiency.
Integrate and manage LLM Observability to trace, debug, and monitor every extraction
Own systems end-to-end, including(but not limited to) designing, coding, monitoring, testing, CI/CD and on-call support.

4+ years of experience as a software engineer, primarily with Python
2+ years of hands-on experience building and deploying applications that use Large Language Models (LLMs)
Experience in extracting structured JSON from text using LLMs and a deep understanding of Prompt Engineering
Proficiency in classic NLP libraries for tasks like NER, text classification, and pre-processing
Experience with LLM tracing, debugging and evaluation platforms such as Langfuse
Excellent communication, organizational, problem-solving, debugging, and analytical skills

Ideally, you possess an advanced degree (Bachelor's / Master's) in Computer Science, Computer Engineering, or a relevant field with a focus on Artificial Intelligence, machine learning, but equivalent industry experience may be considered
Experience in async processing of data at scale
Using frameworks like LangChain, HuggingFace, and backend web frameworks like FastAPI
Expertise on core engineering skills - Cloud, microservice architecture, caching, and queuing
Familiarity with concepts/tools as Docker, k8s, VCS, CI/CD
Previous experience in data extraction from specific domains (e.g., financial reports, news)

Remote (Worldwide) — U.S., U.K., Finland, India, Singapore, Canada, Ireland

AlphaSense is hiring a Senior Software Engineer (AI Applications)