Implement A2A integration patterns (APIs, webhooks, event streams, connectors)
Create reusable SDKs, templates, and reference implementations for AI features
Query logs and metrics to understand model performance in production
Design and maintain evaluation pipelines for AI features
Instrument AI features with observability and testing
Design and implement AI-backed services and APIs in Python using PyTorch
Collaborate with customer-facing teams to turn customer feedback into improvements
Join customer calls and workshops to understand their systems and constraints

Requirements

8+ years of software engineering experience with 2+ years working with ML/AI or LLM-based applications
An inventive mind looking for the best solutions to interesting problems
Strong sense of mentorship and team building
Current understanding of the state of AI
Expertise in Python, including hands-on work with PyTorch or similar frameworks
Familiarity with A2A integration patterns: REST/gRPC APIs, webhooks, queues, or event-driven systems
Comfortable with data-analyst-style work: Writing SQL and using analytics tools/notebooks
Experience with at least one cloud platform (AWS / GCP / Azure)
Exposure to LLM applications (RAG, agents, prompt pipelines)
Experience with logging/observability stacks (e.g., OpenTelemetry, Prometheus/Grafana, Datadog)
Familiarity with MLOps/LLMOps concepts: evaluation harnesses, prompt/version management, feature flags, or canary rollouts
Proficiency in Java/Scala, along with associated frameworks
Proven track record of shipping production features and iterating based on feedback
Strong communication skills with the ability to explain technical details and data insights

Benefits

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

PythonPyTorchSQLJavaScalaMLOpsLLMOpsA2A integration patternsevent-driven systemslogging/observability

mentorshipteam buildingcommunicationproblem-solvingcollaboration