Senior Software Engineer - Artificial Intelligence/Machine Learning (5-7 yrs)

Job Overview :

We are seeking a passionate Senior Software Engineer (AI Applications) to join our Content Engineering team. This team is at the forefront of large-scale content processing, leveraging cutting-edge technologies.

In this role, you will apply your expertise in Natural Language Processing (NLP) and Large Language Models (LLMs) to extract critical insights from multi-modal documents.

Your contributions will directly enhance AlphaSense's Search and AI products. You'll collaborate with highly skilled engineers to develop robust, scalable solutions for our advanced AI-powered search platform.

Responsibilities :

- Deploy LLM-based, production-grade solutions, ensuring high reliability and performance.

- Fine-tune and adapt State-Of-The-Art (SOTA) LLMs for specialized data extraction tasks, optimizing for specific document types and use cases.

- Develop innovative prompting strategies and architectures to maximize performance when working with confidential business documents.

- Solve complex engineering challenges inherent to LLM solutions, such as high latency and non-deterministic output.

- Implement and scale data extraction pipelines capable of processing high volumes of complex documents with exceptional accuracy and efficiency.

- Work closely with cross-functional teams, including product and research, to translate product requirements into practical machine learning architectures.

- Own systems end-to-end, encompassing design, code, monitoring, and observability for engineering projects.

- Take responsibility for the training, testing, deployment, and iteration cycles for model training projects.

Requirements :

- 5+ years of experience as a software engineer, with primary expertise in Python.

- 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 or Machine Learning, but equivalent industry experience will be considered.

- 2+ years of hands-on experience in NLP problem-solving.

- Proficiency in Applied LLM, with experience developing and deploying NLP/LLM solutions using frameworks like LangChain and HuggingFace.

- Experience with backend web frameworks such as FastAPI.

- Familiarity with experimenting with both Open Source (Llama) and Commercial (Claude) LLMs.

- Deep understanding of Prompt Engineering techniques.

- Excellent communication, organizational, problem-solving, debugging, and analytical skills.

Great to Have :

- Experience in asynchronous processing of data at scale.

- Expertise in core engineering skills: Cloud platforms (AWS, Azure, GCP), microservice architecture, caching, and queuing systems.

- Familiarity with concepts and tools like Docker, Kubernetes (k8s), Version Control Systems (VCS), and CI/CD pipelines.