Senior Software Engineer, AI Agents (Autonomous Systems) Gaia

Senior Software Engineer, AI Agents (Autonomous Systems) — Gaia Gaia is building the next generation of Gaia.com experiences using AI. This role focuses on designing and shipping agentic, autonomous software systems that can plan, act, evaluate outcomes, and continuously improve—driving real product impact, not demos. You’ll build production-grade AI agents that meaningfully enhance customer experience, operational efficiency, content intelligence, personalization, and discovery across Gaia.com . This is a builder role: you’ll move fast, iterate relentlessly, and own outcomes end-to-end—from problem framing and system design to deployment, observability, and continuous optimization. Responsibilities Architect and implement agentic AI systems that autonomously execute multi-step workflows (planning, tool use, memory, evaluation, refinement). Build and own production services in Python that orchestrate LLM-based reasoning, retrieval, tool calling, and safe action execution. Design autonomy loops: task decomposition, reflection/self-critique, reward signals, evaluation harnesses, and guardrails. Develop robust RAG pipelines for Gaia’s content ecosystem (semantic search, chunking, embeddings, reranking, citations, freshness). Create frameworks for agent reliability: testing, simulation, regression suites, red-teaming, and continuous evaluation. Implement observability for LLM systems: tracing, cost/latency monitoring, failure taxonomy, quality metrics, and incident response. Partner with product, design, and content teams to translate Gaia’s mission and user needs into autonomous capabilities. Optimize for performance and cost: caching, batching, model routing, quantization (where relevant), and prompt/system improvements. Ship continuously: build, measure, learn—tight loops, pragmatic decisions, and visible progress. Qualifications Expert-level Python and experience building production services (APIs, workers, pipelines, orchestration). Deep knowledge of LLMs and agentic systems, including strengths/limits, failure modes, and practical patterns for reliability. Proven track record of execution: you ship, you iterate, you improve outcomes based on real signals. Strong “builder + owner” mindset: you take ambiguous problems, create clarity, and deliver results. Entrepreneurial mindset: bias toward action, comfort with uncertainty, high accountability, and strong product instincts. Solid foundation in mathematics, statistics, and data reasoning (you can quantify uncertainty, validate improvements, and avoid hand-wavy conclusions). Strong data fluency: instrumentation, metrics design, experiment analysis, and operational decision-making using data. Strongly Preferred Qualifications Hands-on experience building agentic workflows using modern frameworks (e.g., LangGraph/LangChain, LlamaIndex, Semantic Kernel, or equivalent custom stacks). Experience with tool-using agents: function calling, structured outputs, constrained decoding, and robust schema validation. Experience with evaluation techniques for LLM systems (golden sets, model-graded evals, pairwise ranking, offline/online correlation). Experience with retrieval systems: vector databases, hybrid search, reranking, query rewriting, and content freshness strategies. Knowledge of prompt/system design for production (instruction hierarchies, routing, safety constraints, and jailbreak resistance). Experience with distributed systems and async execution patterns (queues, orchestration, retries, idempotency, backpressure). Experience deploying and scaling LLM-enabled services in cloud environments (AWS/GCP/Azure), including CI/CD and IaC. Familiarity with MLOps/LLMOps tooling: experiment tracking, model gateways, prompt/version management, and tracing. Experience with privacy/security considerations for AI systems (PII handling, data minimization, auditability). Front-end or full-stack capability is a plus (you can ship end-user impact, not just back-end components). Prior work in consumer subscription products, content platforms, personalization, or discovery systems. Designing clean architectures for autonomous agents: planners, executors, tool registries, memory stores, and evaluation loops. Strong API design instincts and comfort with typed interfaces, schemas, and contracts. Ability to write maintainable, well-tested code and to improve legacy systems pragmatically. Strong debugging skills across model behavior, orchestration logic, and distributed runtime issues. Practical understanding of tradeoffs between different model families, context sizes, latency profiles, and cost. You don’t get stuck in “research mode.” You prototype quickly, then harden what works. You seek truth with data: you measure quality, cost, and reliability, and you improve what matters. You communicate clearly: you can explain agent behavior, failure modes, and tradeoffs to technical and non-technical partners. You care about craft and user value: autonomy is only useful if it’s safe, reliable, and genuinely improves the experience. You are genuinely excited about Gaia’s subject matter and mission, and you want to build with that context in mind. Example Problems You Might Own An autonomous “Content Intelligence Agent” that tags, summarizes, cross-links, and recommends Gaia content with measurable improvements to discovery and retention. A “Personalization Agent” that builds an evolving user understanding (with privacy safeguards) and drives next-best actions across the product. An internal “Ops Agent” that autonomously triages issues, proposes fixes, drafts release notes, and supports content/metadata workflows with guardrails. A “Member Support Agent” that resolves issues end-to-end with tool access (account actions, refunds, troubleshooting) safely and audibly. What Success Looks Like (90–180 Days) You’ve shipped at least one production agentic capability with clear metrics (quality, adoption, cost, latency, reliability). You’ve established an evaluation and observability loop so the system gets better week-over-week. You’ve raised engineering standards for AI agent development: testing, tracing, safety, and maintainability. You’re a force multiplier—other teams can build on the platform you create. Compensation Range: $75000 - $90000 (USD) More About Gaia Gaia exists as a transformational network to empower a global conscious community. Gaia (Nasdaq: GAIA) is a publicly traded company in Louisville, Colorado. We offer global video streaming of over 8,000 original series, shows, films, documentaries, and practices for conscious living to our members in over 190 countries. Our vast video library serves as a vessel for the community we seek to empower. We are not a subscription service that streams whatever pays our bills. Our content goes deep into select niches of Seeking Truth, Transformation, Alternative Health and Yoga channels. We often cover subjects that other media companies won’t touch. We expect you did explore Gaia’s library of original shows, documentaries, and films. If our work on ancient wisdom, who are we, our true history, coverups, and metaphysics resonates, you might be a good fit for Gaia. We seek to hire and inspire employees who embrace our mission to empower a global conscious community, who hope their work empowers our community of inspired members, to be a catalyst of transformation. The best work we do every day is to remember our vision is “to empower the evolution of consciousness.” The perks of working collaboratively with a team dedicated to sharing this mission include an on-site gym; a beautiful solar-powered campus, complete with hiking and running trails, community garden, and a labyrinth; and an on-site, mostly organic café that serves breakfast and lunch daily including a full-service espresso bar featuring locally roasted coffee. Full-time employees are offered alternative and traditional medical benefits including preventative coverage; as well as dental, vision, 401K, and life insurance. #J-18808-Ljbffr