Senior Software Engineer, Agentic AI
New
O
OrbisAI software
Remote - US & Middle EastFull-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 4+ years of professional software engineering experience, including 2+ years building LLM-backed or agentic systems in production
- Required Skills
- PythonTypeScript
Requirements
- Have 4+ years of professional software engineering experience, including 2+ years building LLM-backed or agentic systems in production.
- Hold a bachelor's degree in computer science, a related technical field, or have equivalent professional experience.
- Have strong programming skills in Python and/or TypeScript, with substantial production code in at least one.
- Bring practical experience with retrieval-augmented generation, including embeddings, vector search, chunking strategy, ranking, and their failure modes.
- Have experience building and debugging multi-step, tool-using agents, using a framework or primitives.
- Demonstrate rigor in evaluation, including harnesses that measure whether AI changes improve outcomes.
- Be willing to travel up to 15%.
- Knowledge of knowledge graphs, ontologies, entity resolution, or information extraction is desirable.
- Experience running open-weight models in constrained or disconnected environments is desirable.
- Experience with production observability and cost control for model-backed workloads is desirable.
- Familiarity with OSINT, intelligence, or research workflows and their accuracy and provenance expectations is desirable.
- Experience mentoring engineers into AI work, open-source contributions, publications, or academic collaboration in applied AI is desirable.
Responsibilities
- Architect and ship knowledge, tool, and goal-driven agents across the portfolio.
- Own agent orchestration, 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 how conclusions were reached.
- Own agent-quality evaluation infrastructure for accuracy, groundedness, explainability, latency, and cost.
- Integrate model providers and third-party tools behind stable internal interfaces.
- Instrument agents to surface quality regressions and cost anomalies.
- Partner with research engineers to productionize validated results and mentor engineers moving into AI work.
View Full Description & ApplyYou'll be redirected to the employer's site
