AI Solution and Platforms Junior Architect/Engineer

• Write production-grade Python for observability tooling — custom OTEL exporters, signal aggregators, anomaly detectors, and data transformation pipelines — adhering to team engineering standards.
• Apply basic statistical and data science methods to telemetry data — time-series analysis, threshold tuning, distribution characterization — to improve signal quality and alerting precision.
• Contribute to Python SDK and library development that simplifies OTEL onboarding for agent developers across the organization.
• Participate in code reviews, apply test-driven development practices, and continuously improve the quality and maintainability of the observability codebase.

Agent Fleet, Physical AI & Multi-Modal Observability (5%)

• Implement telemetry for agent fleet coordination — capturing spawn/termination events, inter-agent communication traces, load distribution metrics, and fleet health indicators.
• Contribute to observability instrumentation for physical AI pipelines (edge inference, sensor fusion, robotics control loops) as directed — focusing on latency, reliability, and data quality signals.
• Add OTEL instrumentation to multi-modal model pipelines — tracing vision, audio, and text input processing stages and capturing cross-modal alignment quality signals.

Agentic Marketplace, Registry & A2A / UCP / AP2 Observability (5%)

• Instrument the Agentic Marketplace and Agent Registry with usage telemetry — tracking agent invocations, capability health scores, adoption trends, and dependency relationships.
• Implement protocol-level observability for A2A (Agent-to-Agent), UCP, and AP2 communication flows — capturing message latency, error rates, retry patterns, and trust boundary crossings.
• Contribute to Marketplace Observability Dashboard development — building data connectors, metric calculations, and visualization components as directed by the L11.

• Collaborate closely with AI platform engineers, data scientists, SRE, and product teams to gather requirements, align on telemetry standards, and resolve integration friction.
• Participate in agile ceremonies — sprint planning, stand-ups, retrospectives — contributing to estimation, dependency identification, and delivery transparency.
• Stay current with emerging observability frameworks, OTEL specifications, agent communication protocols, and AI safety research — sharing learnings with the team regularly.
• Contribute to internal documentation, engineering wikis, and onboarding guides for the observability platform.
• Bachelor's or Master's degree in Computer Science, Software Engineering, AI/ML, Data Science, or a related technical field.
• 4–8 years of experience in software engineering, platform engineering, or data engineering — with at least 2 years of hands-on work in observability, monitoring, or distributed systems.
• Demonstrated ability to deliver production-grade software in a team environment; track record of completing complex technical features end-to-end.
• Python Proficiency: Strong Python engineering skills — writing clean, testable, maintainable production code; familiarity with async patterns, type hints, and modern Python tooling (Poetry, Ruff, pytest).
• Observability Fundamentals: Solid working knowledge of the three pillars of observability (metrics, logs, traces); ability to instrument services with OpenTelemetry (OTEL) SDKs; understanding of trace context propagation and semantic conventions.
• Distributed Systems: Working knowledge of microservices, event streaming (Kafka or equivalent), REST/gRPC APIs, and containerized deployment (Docker, Kubernetes).
• Cloud Platforms: Hands-on experience with at least one major cloud provider (Azure, AWS, or GCP) — including managed services, IAM basics, and cost awareness.
• CI/CD & DevOps: Experience building or contributing to CI/CD pipelines; familiarity with GitOps, infrastructure-as-code concepts, and automated testing frameworks.
• Data Fundamentals: Ability to query, analyze, and visualize time-series and log data using tools such as Grafana, Datadog, Splunk, Prometheus, or equivalent.
• Hands-on experience with agentic AI frameworks (LangChain, LangGraph, AutoGen, Semantic Kernel, CrewAI, or equivalent).
• Contributions to open-source observability projects or OTEL community.
• Familiarity with reinforcement learning concepts, self-supervised learning, or model fine-tuning workflows.
• Experience with security tooling relevant to AI (adversarial robustness libraries, LLM safety frameworks, or red-team toolkits).
• Exposure to Responsible AI frameworks, fairness evaluation libraries ( Arize, Fairlearn, AI Fairness 360), or explainability tools (SHAP, LIME).
• Experience in a fast-paced AI platform, MLOps, or LLMOps role with production deployment responsibilities.