This position focuses on building and improving agentic AI platform capabilities. The role involves developing intelligent agents, workflows, and integrations while ensuring reliability, safety, and strong engineering practices throughout the AI lifecycle.
Grade Level (for internal use): 05
Key Responsibilities
- Design and develop agentic AI platform components including agents, tools, workflows, and integrations with internal systems.
- Implement observability across the AI lifecycle with tracing, logging, metrics, and evaluation pipelines to track agent quality, reliability, and cost.
- Translate business problems into AI solutions by working with product teams, subject matter experts, and platform engineers to define data, model, and orchestration needs.
- Build and maintain data pipelines and datasets used for training, evaluation, grounding, and safety of LLM-based agents.
- Drive experimentation and benchmarking by testing prompts, models, and agent workflows, then analyzing results to guide improvements.
- Implement guardrails and safety checks for prompts, tool usage, system access, and output filtering to maintain safe and compliant AI operations.
- Create documentation and engineering guidelines, and share best practices related to agentic AI patterns, observability-first engineering, and ML/data hygiene.
Core Skills Required
- Strong programming background in Python (preferred) or similar languages.
- Understanding of LLM and Generative AI fundamentals, including prompting, embeddings, vector search, retrieval augmented generation, and agent workflows.
- Experience running production workloads or data pipelines on AWS, Azure, or GCP, including containers, serverless services, and managed storage.
- Hands-on experience with observability tools such as OpenTelemetry, Prometheus, Grafana, or ELK for logs, metrics, and tracing.
- Working knowledge of structured and unstructured data with strong SQL skills and frameworks like Pandas, Spark, or dbt.
- Ability to evaluate trade-offs around system reliability, performance, and operational cost.
Qualifications
- 0 to 6 years of experience in software engineering, data engineering, ML engineering, data science, or MLOps.
- Bachelor’s or Master’s degree in Computer Science, Engineering, Data Science, or equivalent practical experience.
- Familiarity with CI/CD pipelines, code reviews, and modern engineering practices.
- Nice to Have:Â exposure to agentic AI frameworks such as LangChain, LangGraph, or OpenAI Agents.
Our Mission
Advancing Essential Intelligence.
