Mid-Level Software Engineer, Revenue Stories

Responsibilities:

• Improve and optimize critical LLM inference pipelines to generate high-quality deal assessments while maintaining cost efficiency.
• Develop and implement new AI features, such as integrating external data sources (e.g., company news) into deal risk assessments.
• Enhance monitoring systems to improve pipeline visibility, accelerate debugging, and reduce failure resolution time by 50%.
• Scale inference pipelines effectively to handle increased volumes, targeting 5 million AI-generated insights monthly.
• Write clean, maintainable, and well-documented code, following engineering best practices.
• Build tooling to enable customer support teams to independently resolve common issues.
• Demonstrate behaviors consistent with our Engineering Leveling Guidelines.

Requirements:

• 3+ years professional experience developing distributed systems in a cloud environment (AWS preferred).
• Strong experience analyzing large structured and unstructured datasets.
• Proficiency with Spark or equivalent big data processing engines (Hive, Hadoop, MapReduce, Storm, Samza).Experience using Large Language Models (LLMs), familiarity with prompting techniques (chain-of-thought, RAG), and knowledge of common market models.
• Understanding of LLM limitations and strategies to mitigate them.
• Proven problem-solving abilities, with practical and elegant coding solutions.
• Passionate about engineering excellence—advocates for high-quality, reliable, and maintainable software.
• Experience improving existing codebases, automation, and tooling for operational efficiency.
• Bachelor’s Degree in Computer Science, Computer Engineering, or closely related discipline.


Nice to Have:
• Familiarity with Elasticsearch and Kafka.
• Experience with fine-tuning or advanced inference techniques for LLMs.