
Software Engineer, AI
Posted 1 day ago

Posted 1 day ago
This is a fully remote position, open to applicants in California.
• Participate in the design, development, maintenance, and deployment of AI agent systems, including LangGraph StateGraph patterns, CrewAI multi-agent orchestration, LlamaIndex data/agent workflows, or similar frameworks.
• Create, develop, and manage FastAPI-based agent servers, including async/await endpoints, streaming responses, and health check endpoints, in accordance with established architectural and coding standards.
• Establish thorough testing strategies — unit, integration, edge-case, and performance — for agents and services to guarantee reliability in production.
• Implement and enhance guardrails for AI interactions, which encompass input/output validation, safety checks, prompt hardening, policy enforcement, and effective error handling in line with organizational security and compliance standards.
• Develop secure tool execution patterns that follow least-privilege access, allowlists, secrets management, audit logging, and validation controls against prompt injection/data exfiltration under the guidance of senior engineers.
• Create agent observability features including per-step traces, tool-call telemetry, cost/latency budgets, and SLO-based alerting using existing monitoring and logging tools.
• Assist in designing and maintaining agent evaluation sets, adversarial tests, regression tests, and monitoring systems for safety/quality drift.
• Design and construct RAG/retrieval pipelines using vector databases such as Chroma, Milvus, Weaviate, and Qdrant, collaborating with data and platform teams on schema and performance optimization.
• Work with SMEs across Platform Engineering, Data Science, Security, Quality, and Product to ensure that agent systems fulfill technical and operational requirements.
• Aid in the creation, modification, and upkeep of AI system documentation, including architecture decision records (ADRs), runbooks, API specifications, network topology diagrams, data flow diagrams, and best-practice guides.
• Provide technical insights regarding operability, technical feasibility, engineering design, security posture, maintainability, and documentation necessities.
• Support the planning and execution of AI agent-based projects and solutions in collaboration with cross-functional teams, aiming to meet cost, timeline, and quality goals.
• Implement and facilitate containerized deployment, start-up, commissioning, and release qualification activities using Docker multi-stage builds, dependency management, and best practices for container health checks.
• Collaborate with and learn from senior engineers; may occasionally mentor less experienced engineers through code reviews and collaborative troubleshooting of AI agent and service-related issues.
• Adhere to and enhance Standard Operating Procedures (SOPs), process improvements, and standard engineering templates for agent development.
• Monitor agent performance and reliability, gather metrics and logs, and utilize data to propose and implement optimization opportunities.
• A Bachelor's degree in Computer Science, Software Engineering, or a related field with a minimum of 3 years of relevant software development experience is required.
• At least 2 years of practical Python development experience, demonstrating proficiency in Python 3.12+ and modern language features (type hints, async/await, etc.) is required.
• A minimum of 2 years of hands-on Typescript development experience.
• Experience with at least one AI agent framework (such as LangGraph, LangChain, CrewAI, or LlamaIndex) in a production or near-production environment is required.
• Proven experience in building and running containerized applications with Docker, including multi-stage builds and foundational DevOps practices, is required.
• Experience in troubleshooting and optimizing systems in an enterprise or regulated setting is preferred.
• Familiarity with working in an organization that has formal change control, compliance, or audit requirements is preferred.
• Medical, Dental and Vision Plan Options
• Health and Financial Wellness Programs
• Employer Assistance Program (EAP)
• Company Paid and Voluntary Life/AD&D, Short-Term and Long-Term Disability
• Healthcare and Dependent Care Flexible Spending Accounts
• 401(k) Retirement Plan with Company Match
• 529 Education Savings Program
• Voluntary Legal Services, Identity Theft Protection, Pet Insurance and Employee Discounts, Rewards and Perks
• Paid Time Off (PTO) includes: 11 Holidays
• Exempt Employees are eligible for Unlimited PTO
• Non-Exempt Employees are eligible for 10 Vacation Days, 56 Hours of Health Pay, 2 Personal Days and 1 Cultural Day
• Tools and resources to optimize your Health and Wellness
VPS
Tango
Influur
Salesloft
Get handpicked remote jobs straight to your inbox weekly.