Staff Software Engineer

This role requires a blend of technical expertise, leadership skills, and the ability to foster a collaborative and innovative environment. We are looking for a Project Lead familiar with cloud-native and AI-native development practices. Our software is built around AI at its core—LLMs, agents, and retrieval systems—and runs on IaaS (Google Cloud/AWS/etc.), so familiarity with these environments and their managed AI services is a plus. Full ownership of your code will be encouraged, including deployment, testing, evaluation, and validation of both traditional and AI components. You will lead a team of software and AI engineers, coaching and mentoring them. Familiarity with CI/CD, test-driven development, and evaluation-driven development (eval harnesses for AI features) will be a benefit.

Responsibility Area: Software Development

• Develop intuitive AI-native software that meets and exceeds the needs of the company
• Development of technical specifications and planning, including model selection, prompt/agent design, and data/retrieval architecture
• Analyze and automate tests for software components prior to delivery, and build evaluation harnesses (accuracy, regression, and hallucination checks) for AI features
• Troubleshoot coding and model-behavior problems quickly and efficiently to ensure a productive workplace
• Follow secure software coding practices, including AI-specific safeguards (prompt-injection defense, data privacy, PII handling, and responsible-AI guardrails)
• Professionally maintain all software and create updates regularly to address customer and company concerns, including monitoring model performance and drift in production
• IaaS procedures and practices, including managed AI/ML services (e.g., Bedrock/SageMaker, Azure OpenAI, Vertex AI)
• Experience with Kubernetes and containerization is welcome; experience serving models or deploying inference/GPU workloads is a plus

Responsibility Area: Communication

• Communicate effectively and professionally in all forms of communication with internal and external customers
• Liaise with team members, management, and clients
• Be transparent about challenges, failures, and successes, including the limitations and non-deterministic nature of AI systems
• Deliver presentations and write progress reports for stakeholders, translating AI capabilities and trade-offs for both technical and non-technical audiences
• Actively seek ways to improve business software processes and interactions, including where AI and automation can add value

 

Responsibility Area: Leadership

• Manage individual contributors' daily tasks
• Mentor software and AI engineers to ensure high product quality across both deterministic code and AI/model behavior
• Perform detailed code reviews, including reviews of prompts, agent logic, and evaluation results
• Evaluate performance, provide feedback and constructive criticism to team members
• Set and track quarterly goals for all team members
• Assist with training and recruitment activities
• Provide status updates, weekly reports, and issue details to senior leadership as needed
• Participate in Root Cause Analysis for customer-reported issues, including failures rooted in model behavior, hallucinations, or data/retrieval quality
• Aid and support the coaching and training of other team members to ensure all employees are confident in the use of software applications and AI tooling
• Collaborate closely with cross-functional teams including product management, domain specialists, and engineering to define requirements and develop scalable AI-driven solutions
• Stay current with the latest advancements in AI and related technologies (new models, frameworks, and techniques), and proactively identify opportunities to apply them to our products and services

 

 

• 8-12 years of practical Java experience
• 2 years of experience with prompt engineering and prompt/agent scripting
• 2 years of hands-on experience integrating third-party AI/ML services and platform APIs (e.g., OpenAI, Anthropic, Salesforce and other SaaS)
• Proven ability to design and manage domain-specific languages, prompt templates, and agent instruction frameworks
• Develop and optimize microservices that power high-performance data and embedding pipelines, handling up to 10 million rows and feeding vector stores
• Proficiency in Python, Java, and JavaScript, with strong Python skills for the ML/AI ecosystem
• Experience with RESTful and streaming APIs, model/inference endpoints, web services, and integration technologies
• Knowledge of cloud computing and managed AI services (e.g., AWS Bedrock/SageMaker, Azure OpenAI, Google Vertex AI)
• Create customer-centric AI solutions such as RAG assistants, agentic workflows, and AI-driven customer service
• Create data and knowledge-base migration tools for SaaS applications, including moving embeddings and vector data between cloud instances
• Experience with LLM orchestration and retrieval frameworks (e.g., LangChain, LlamaIndex) and vector databases (e.g., Pinecone, Weaviate, pgvector)
• Outstanding collaboration and communication skills
• Strong problem-solving and debugging skills, including working with non-deterministic AI outputs
• Ability to learn quickly, take direction, work independently, and as part of a team
• Ability to develop unit tests and AI evaluation harnesses (accuracy, regression, and hallucination checks) for code components, prompts, and complete applications
• Ability to debug and isolate the root cause of complex issues in probabilistic and distributed systems
• Experience with Agile and Scrum development methodologies
• Experience with Spring Boot or similar frameworks
• Experience working with APIs, REST standards, JSON, SQL, and NoSQL/vector stores
• Bachelor's degree in computer science or a related field; coursework or experience in ML/AI a plus