Note: The job is a remote job and is open to candidates in USA. Tango Analytics helps businesses make smarter decisions through technology, data, and collaboration, with a focus on real estate technology. The Senior Applied AI Engineer will build and ship production AI agents and generative AI capabilities, owning agent architecture, retrieval, evaluation, safety, observability, and deployment. The role partners with Product, Engineering, and domain experts to develop reliable AI solutions for corporate real estate, workplace management, lease administration, and retail location management.
Responsibilities
- Design, build, and ship production AI agents on LangGraph, keeping the agent layer portable across cloud platforms
- Own agents end to end: graph design, tool definitions, prompt and context engineering, durable execution, failure and retry behavior, and cost and latency budgets
- Build agent tooling against internal systems over MCP, using direct API calls where those are the better fit, and agent-to-agent interfaces as agents begin to compose
- Deliver human-in-the-loop review flows, including interrupt points, confidence surfacing, and the correction paths that let a customer review and override agent output
- Build and tune retrieval, covering chunking, hybrid retrieval, grounding, and citation back to source page and paragraph
- Contribute the evaluations for the agents you ship: golden datasets, LLM-as-judge and deterministic scorers, and regression suites that run in CI, built against the shared evaluation harness the platform provides
- Diagnose quality failures to root cause, whether retrieval miss, prompt defect, tool error, model regression, or flawed ground truth, and correct the appropriate layer
- Own agent-level safety behavior, including prompt-injection resistance, PII handling, and refusal and escalation paths, applying the platform guardrail service maintained by Platform Engineering
- Partner with Product to translate accuracy thresholds, confidence disclosure, and human-in-the-loop triggers into shipped behavior
- Work with Platform Engineering on deployment, and with Data Platform on the curated datasets agents read
- Feed curated agent session and usage analytics into the warehouse so agent performance is measurable alongside product analytics
- Transition reference agents to the domain teams that will operate them long-term, and contribute to the shared agent quality standard
Skills
- 7+ years of professional software engineering experience, including 2+ years building LLM-powered systems that reached production and real users
- Strong expertise with Python and its service stack (FastAPI, Pydantic, or equivalents), along with the engineering discipline that supports it: testing, code review, CI/CD, and production ownership
- Production experience with an agent orchestration framework. LangGraph strongly preferred; LangChain, OpenAI or Claude Agents SDKs, or equivalent frameworks considered
- Hands-on depth with at least one frontier model API
- Hands-on experience with LLM evaluation: golden datasets, LLM-as-judge and deterministic scorers, regression testing, and using evaluation results to gate releases. This is central to the role
- Experience with MCP tool servers or comparable tool and function-calling protocols, and with multi-agent patterns
- Production RAG and retrieval experience, including chunking strategy, hybrid retrieval, grounding, citation, and diagnosing retrieval failures
- Experience with LLM observability and tracing (LangSmith, Langfuse, Arize, or equivalent), and with prompt and version management
- Sound judgment about failure modes such as hallucination, prompt injection, and silent degradation, with the ability to distinguish acceptable failures from unacceptable ones
- Applicants must be authorized to work in the U.S. for any employer
- We cannot sponsor employment-based visas at this time
- 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
Benefits
- Health, dental, and vision insurance
- A 401(k) plan with company match
- Flexible work arrangements, including remote, hybrid, or in-office options
- An inclusive and collaborative culture where diverse perspectives are valued, teamwork is encouraged, and everyone has a voice
Company Overview