Principal Software Engineer, AI Agents & Generative AI

Ability to work effectively in a fast-paced, dynamic environment and manage multiple priorities simultaneously

Qualifications

• Bachelor's degree in Computer Science, Systems Engineering, Software Engineering, or a related field. Advanced degrees are preferred but not required.
• Must be a U.S. Citizen
• 7 years of proven experience in a relevant technology domain, with preference for Software engineer and AI/ML
• ‘Strong understanding of technical concepts related to managing cloud-based data and machine learning pipelines (e.g., AWS or GCP)
• Significant software development experience with Python, JavaScript, or similar
• Preferred Skills
• Familiarity with vector databases, embeddings, and retrieval-augmented generation(RAG) architectures.
• Knowledge of distributed systems design and high-availability architectures supporting global-scale workloads.
• Leverages AI for team velocity and upskilling, including using AI-assisted development heavily, prototyping quickly, automating repetitive engineering tasks and moving faster than traditional SWE teams.
• Excellent communication and interpersonal skills
• Ability to work independently and collaboratively with remote and/or geographically distributed teams
• Ability to work effectively in a fast-paced, dynamic environment and manage multiple priorities simultaneously
• Pay Transparency: To support pay transparency, Vantor includes salary ranges in all U.S. job postings. Starting pay for this role will fall within the listed range and will be based on factors such as experience, qualifications, skills, location, and market conditions. Candidates who meet the minimum requirements for the role should not expect to receive compensation at the top of the range. The listed range reflects the expected pay for this position, and final offers will be determined based on each candidate’s experience, expertise, and alignment with the role.
• For all other states, we use geographic cost of labor as an input to develop market-driven ranges for our roles, and as such, each location where we hire may have a different range.

Responsibilities

• Design, develop, and deploy AI-native software products that transform large-scale geospatial data into actionable intelligence and mission-critical insights.
• Implement multi-agent workflows using modern orchestration frameworks (e.g., Google ADK, LangChain, LangGraph) to enable autonomous reasoning, planning, and execution.
• Integrate state-of-the-art Large Language Models (GPT-4, Claude, Gemini, etc.) to power contextual analysis, hypothesis generation, and adaptive decision-making.
• Engineer agents capable of dynamic tool use, structured reasoning, and iterative self-refinement to improve insight quality over time.
• Develop robust data ingestion and transformation layers to support pattern-of-life, detection, anomaly identification, and predictive analytics
• Ensure secure, scalable integrations across cloud and enterprise environments.
• Create feedback loops and reinforcement mechanisms to iteratively improve model reliability and operational trustworthiness.
• Deploy and operate AI systems in production using modern DevOps practices (containerization, orchestration, CI/CD).
• Leverage AI development agents (e.g., Codex, Gemini CLI, Claude Code) as force multipliers for software design, implementation, testing, and documentation.
• Contribute to shared engineering standards, documentation, and best practices for AI-first development.