Technical Analyst – AI Agents, LLM & Backend Engineering Job Summary

★

Ranking: 2639

Participar

Key Responsibilities

Design and support AI Agent architectures involving planning, tool/function calling, memory, context engineering, semantic routing, workflows, and multi-agent orchestration.
Work with MCP (Model Context Protocol) and, ideally, A2A concepts.
Develop and optimize agent runtimes covering execution loops, state management, orchestration, retries, checkpointing, streaming, concurrency, human-in-the-loop, and tool execution.
Contribute to AI evaluation frameworks, including offline/online evaluations, benchmark design, golden and synthetic datasets, LLM-as-a-Judge, pairwise comparison, regression testing, and experiment tracking.
Work with MLflow to support reproducible AI experimentation and evaluation.
Build and optimize RAG pipelines, including chunking, embeddings, reranking, vector databases, retrieval quality, and context management.
Apply LLM engineering practices including prompting, structured outputs, JSON Schema, function calling, tokenization, caching, latency and cost optimization, and reasoning models.
Develop scalable backend services using Python, with FastAPI being highly desirable.
Work with technologies such as Docker, Kubernetes, Redis, Kafka, and PostgreSQL.
Implement observability using OpenTelemetry, tracing, metrics, logs, agent traces, and cost/latency monitoring.
Support testing through unit tests, integration tests, evaluation testing, regression suites, and CI/CD for AI applications.
Work with cloud platforms such as Azure, AWS, or GCP, with experience in Azure OpenAI, Vertex AI, or Amazon Bedrock/AgentCore being highly desirable.

Required Skills

3+ years of technical development experience.
Strong Python development skills — mandatory.
Understanding of backend development and API architectures.
Knowledge of Generative AI, LLMs, and AI Agent architectures.
Familiarity with RAG, tool/function calling, and agent orchestration.
Understanding of software testing, observability, and production engineering.
Strong analytical and problem-solving skills.

Desirable Technologies

Technical Analyst – AI Agents, LLM & Backend Engineering Job Summary

★

Ranking: 2639

Participar

Key Responsibilities

Design and support AI Agent architectures involving planning, tool/function calling, memory, context engineering, semantic routing, workflows, and multi-agent orchestration.
Work with MCP (Model Context Protocol) and, ideally, A2A concepts.
Develop and optimize agent runtimes covering execution loops, state management, orchestration, retries, checkpointing, streaming, concurrency, human-in-the-loop, and tool execution.
Contribute to AI evaluation frameworks, including offline/online evaluations, benchmark design, golden and synthetic datasets, LLM-as-a-Judge, pairwise comparison, regression testing, and experiment tracking.
Work with MLflow to support reproducible AI experimentation and evaluation.
Build and optimize RAG pipelines, including chunking, embeddings, reranking, vector databases, retrieval quality, and context management.
Apply LLM engineering practices including prompting, structured outputs, JSON Schema, function calling, tokenization, caching, latency and cost optimization, and reasoning models.
Develop scalable backend services using Python, with FastAPI being highly desirable.
Work with technologies such as Docker, Kubernetes, Redis, Kafka, and PostgreSQL.
Implement observability using OpenTelemetry, tracing, metrics, logs, agent traces, and cost/latency monitoring.
Support testing through unit tests, integration tests, evaluation testing, regression suites, and CI/CD for AI applications.
Work with cloud platforms such as Azure, AWS, or GCP, with experience in Azure OpenAI, Vertex AI, or Amazon Bedrock/AgentCore being highly desirable.