Skip to contentSoftware Engineer AI
| Company | Salesforce |
|---|
| Location | San Francisco, CA, USA |
|---|
| Salary | $172000 – $236500 |
|---|
| Type | Full-Time |
|---|
| Degrees | Bachelor’s |
|---|
| Experience Level | Senior |
|---|
Requirements
- 5+ years of experience in software engineering as an individual contributor.
- Proficiency in Python and data analysis tools like SQL, Spark, or Pandas.
- Understanding of and experience with modern ML/AI technologies, including natural language processing (NLP) and LLMs (e.g., GPT-3+, open source models, etc.), RAG architectures, Agent-based systems and their applications with a track record of evaluating new technologies.
- Understanding of information retrieval concepts, relevance metrics (e.g., precision@k, recall, NDCG), and user engagement metrics.
- Experience with statistical analysis, experimentation frameworks, and A/B testing in a production environment.
- Strong understanding of LLM behavior, prompt design strategies (e.g. few-shot, chain-of-thought), and evaluation methods. Experience with LLM APIs (e.g., OpenAI, Anthropic, or Hugging Face) is required.
- Bachelor’s degree or equivalent experience in Computer Science, Software Engineering, or a related technical field.
Responsibilities
- Develop foundational features from the ground up powered by LLMs.
- Improve LLM and RAG models for various e-commerce workflows using various techniques from domain search and vector-based retrieval.
- Optimize prompts that drive high-performing outputs from large language models in real-world applications.
- Design and implement evaluation and logging systems to monitor performance.
- Design, implement, and refine metrics to measure the quality and performance of search, recommendation and agentic systems (such as NDCG, MRR, CTR, conversion rate, and revenue per session) on the commerce platform.
- Develop automated pipelines for evaluating algorithmic changes using A/B testing and offline evaluation frameworks.
- Analyze user behavior signals (clicks, dwell time, scroll depth, etc.) to derive actionable insights about search relevance and customer intent.
- Ability to wear multiple hats: research, coding, planning, brainstorming, interviewing, and cross-team collaboration.
Preferred Qualifications
- Nice to have: familiarity with search technologies (e.g., Elasticsearch, Solr, Lucene) and ML-powered ranking systems.
- Are highly ambitious and driven and set high goals for yourself and others.
