Senior Applied AI Engineer

Tango is seeking a Senior Applied AI Engineer based in Oregon (onsite) to build and ship Tango’s first AI-powered product. The role focuses on converting generative AI and machine learning into dependable, production-ready capabilities across agent design, retrieval, evaluation, safety, and cross-functional delivery.

Responsibilities

• Design, build, and ship production AI agents on LangGraph, keeping the agent layer portable across cloud platforms.
• Own agents end to end, including graph design, tool definitions, prompt and context engineering, durable execution, failure and retry behavior, and cost and latency budgets.
• Build agent tooling that integrates with internal systems using MCP, using direct API calls where they are a better fit, and enabling agent-to-agent interfaces as agents compose.
• Deliver human-in-the-loop review flows, including interrupt points, confidence surfacing, and correction paths that allow customer review and override of agent output.
• Build and tune retrieval, including chunking, hybrid retrieval, grounding, and citation back to the source page and paragraph.
• Contribute agent evaluations through golden datasets, LLM-as-judge and deterministic scorers, and regression suites that run in CI based on the platform’s shared evaluation harness.
• Diagnose quality failures to identify root causes such as retrieval misses, prompt defects, tool errors, model regressions, or flawed ground truth, then correct the relevant layer.
• Own agent-level safety behavior, including prompt-injection resistance, PII handling, and refusal and escalation paths using the platform guardrail service maintained by Platform Engineering.
• Partner with Product to translate accuracy thresholds, confidence disclosure, and human-in-the-loop trigger logic into shipped behavior.
• Work with Platform Engineering on deployment, and with Data Platform on curated datasets agents rely on.
• Feed curated agent session and usage analytics into the warehouse so agent performance can be measured alongside product analytics.
• Transition reference agents to domain teams for long-term operation, and contribute to a shared agent quality standard.

Requirements

• 7+ years of professional software engineering experience, including 2+ years building LLM-powered systems that reached production and real users.
• Strong expertise in Python and its service stack (FastAPI, Pydantic, or equivalents), with testing, code review, CI/CD, and production ownership practices.
• Production experience with an agent orchestration framework, with LangGraph strongly preferred; LangChain, OpenAI or Claude Agents SDKs, or equivalent frameworks are acceptable.
• Hands-on depth with at least one frontier model API.
• Hands-on LLM evaluation experience, including golden datasets, LLM-as-judge and deterministic scorers, regression testing, and using evaluation results to gate releases.
• Experience with MCP tool servers or comparable tool and function-calling protocols, plus multi-agent patterns.
• Production RAG and retrieval experience: chunking strategy, hybrid retrieval, grounding, citation, and diagnosing retrieval failures.
• Experience with LLM observability and tracing (LangSmith, Langfuse, Arize, or equivalents), and with prompt and version management.
• Sound judgment on failure modes such as hallucination, prompt injection, and silent degradation, including the ability to separate acceptable failures from unacceptable ones.

Technologies

• Python, FastAPI, Pydantic
• LangGraph, LangChain, OpenAI, Claude Agents SDKs
• MCP, MCP tool servers
• LangSmith, Langfuse, Arize
• RAG, LLM-as-judge, vector and hybrid retrieval stores (pgvector, Pinecone, Weaviate, Qdrant)
• CI/CD, Celery/Redis

Preferred

• Graph-backed agent memory or knowledge graphs (Neo4j or similar).
• Production vector and hybrid retrieval stores (pgvector, Pinecone, Weaviate, Qdrant).
• Async task orchestration for long-running document pipelines (Celery/Redis or equivalent).
• Document intelligence and information extraction at scale, including OCR, layout-aware parsing, and structured extraction from long documents.

Compensation and Benefits

• Salary: USD 160,000 - 190,000 per year
• Competitive Compensation
• Comprehensive benefits: health, dental, and vision insurance
• 401(k) plan with company match
• Generous paid time off
• Flexible work environment (remote, hybrid, or in-office)
• Inclusive and collaborative culture