Senior Software Engineer, Agentic AI

Orbis

1d

About The Position

Own the agentic systems at the center of Orbis AI, including the orchestration, planning, retrieval, and tool-use machinery behind the Agent Catalog and OSINT Agent Harness. Build agents that perform reliably under real mission workloads and establish evaluation standards for the organization. This senior engineering role focuses on correctness, explainability, cost, and behavior at scale.

The role involves architecting and shipping agents, owning orchestration and retrieval systems, building provenance and citation capabilities, and developing evaluation infrastructure. It also includes integrating model providers and third-party tools, monitoring quality and costs, partnering with research engineers to productionize validated results, and mentoring engineers entering AI work. Travel of up to 15% is required for customer engagement, integration support, and team collaboration.

Requirements

• At least 4 years of professional software engineering experience, including at least 2 years building LLM-backed or agentic systems in production.
• Bachelor's degree in Computer Science, a related technical field, or equivalent professional experience.
• Strong programming skills in Python and/or TypeScript, with substantial production code in at least one.
• Deep practical experience with retrieval-augmented generation, including embeddings, vector search, chunking strategy, ranking, and their failure modes.
• Demonstrated experience building and debugging multi-step, tool-using agents, using a framework or primitives.
• Rigor in evaluation, including experience with harnesses that measure whether an AI change improved results.
• Willingness to travel up to 15%.

Nice To Haves

• Experience with knowledge graphs, ontologies, entity resolution, or information extraction.
• Experience running open-weight models in constrained or disconnected environments where a hosted API is not an option.
• Experience with production observability and cost control for model-backed workloads.
• Familiarity with OSINT, intelligence, or research workflows and their accuracy and provenance expectations.
• Experience mentoring engineers entering AI work from a conventional software background.
• Open-source contributions, publications, or academic collaboration in applied AI.

Responsibilities

• Architect and ship knowledge agents over customer data, tool agents that wrap external operations, and goal-driven agents that plan and execute multi-step analysis.
• Own the orchestration layer, including planning, tool selection, state and memory, retries, partial failure, and termination behavior.
• Design and own retrieval end to end, including chunking, embedding, indexing, ranking, and query-time behavior.
• Build provenance and citation paths that show users how conclusions were reached, treating unexplainable output as a defect.
• Own evaluation infrastructure for agent quality, measuring accuracy, groundedness, explainability, latency, and cost, and set standards for evaluation cases.
• Integrate model providers and third-party tools behind stable internal interfaces, and instrument agents to identify quality regressions and cost anomalies.
• Partner with research engineers to productionize validated results.
• Mentor engineers moving into AI work from a conventional software background.
• Travel up to 15% for customer engagement, integration support, and team collaboration.

Benefits

• Competitive retirement matching.
• PTO policy that encourages real time off.
• Comprehensive benefits package; a full list is shared with candidates following an initial conversation with the HR team.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior