Senior Software Engineer - AI

Role Overview

Core Engineering Work

• Translate ambiguous product problems into practical AI solutions and select suitable LLM, RAG, agent, deterministic workflow, or traditional software approaches.
• Build Python and FastAPI AI services with asynchronous workers, PostgreSQL, Redis, queues, model APIs, and external tools.
• Build tool-calling agents and multi-step workflows that interact with internal APIs, MCP tools, business systems, and knowledge sources.
• Design event-driven systems with retries, dead-letter handling, idempotency, back pressure, and failure recovery.
• Build RAG systems using ingestion, chunking, embeddings, hybrid retrieval, reranking, metadata filtering, context construction, and citations.
• Create evaluation pipelines using curated datasets, regression tests, retrieval metrics, groundedness checks, and tool-execution evaluation.
• Diagnose hallucinations, retrieval failures, tool misuse, agent loops, latency issues, provider failures, and inference costs.

Required Experience

• Have 5+ years of professional software engineering experience building production backend, distributed, or cloud-based systems.
• Have hands-on production experience with applied AI, LLM, RAG, NLP, or agent-based applications.
• Demonstrate advanced Python, FastAPI, asynchronous programming, Pydantic, SQLAlchemy or SQLModel, and production API development skills.
• Bring strong backend and distributed-systems fundamentals, including REST APIs, concurrency, caching, reliability, and production debugging.
• Have production messaging experience with RabbitMQ, Kafka, Azure Service Bus, or equivalent platforms.
• Have experience integrating LLM APIs, structured outputs, function calling, tool calling, or agent-execution workflows.
• Have built a RAG or knowledge-grounded system with measurable quality and latency outcomes.
• Demonstrate strong PostgreSQL and data-modeling skills and experience with Redis, pgvector, vector databases, or hybrid search.
• Use AI coding agents such as Cursor, Claude Code, Codex, or equivalent tools as part of daily engineering work.

Preferred and Standout Skills

• Preferred knowledge includes prompting, structured outputs, tool schemas, context management, model routing, retries, fallbacks, rate limits, and streaming responses.
• Preferred experience includes Docker, CI/CD, automated testing, observability, distributed tracing, OpenTelemetry, Langfuse, or similar tooling.
• Standout experience includes Semantic Kernel, Microsoft Agent Framework, LangGraph, PydanticAI, or similar agent frameworks.
• Standout experience includes MCP tools and servers, LiteLLM or similar model gateways, Azure AI Search, pgvector, Chroma, Kubernetes, Azure, or OCI.
• High-scale customer-facing AI products, open-weight inference, AI safety controls, and automated agent evaluation systems are valued.

Working Approach